Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

fix: keep only MiMo VoiceDesign

rpone992a710c31f6
diff --git a/.agents/skills/hypit/references/credentials.md b/.agents/skills/hypit/references/credentials.md
index 31b5a90c..9ba66b75 100644
--- a/.agents/skills/hypit/references/credentials.md
+++ b/.agents/skills/hypit/references/credentials.md
@@ -10,7 +10,7 @@ paid/external `build`, configure only variables used by the selected Runtime Pro
| `GOOGLE_CLOUD_PROJECT` | Google Vertex project with Vertex AI enabled |
| `GOOGLE_APPLICATION_CREDENTIALS_JSON` | Vertex credential JSON contents, not a path |
| HypiHub OAuth login | HypiHub default paid provider for generation and Gemini VLM; run `hypit auth login hypihub.default --runtime hypit.runtime.json` and sign in at [hypit.ai](https://hypit.ai) |
-| `MIMO_API_KEY` | Xiaomi MiMo TTS only when explicitly selected |
+| `MIMO_API_KEY` | Xiaomi MiMo VoiceDesign only when the user explicitly selects the official Provider |
Before any paid Build, report the selected Provider and credential source for every paid capability in
the Runtime Profile. Say the variable/store and endpoint (for example, `@hypit/provider-kie` using
diff --git a/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md b/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
index 6a1de536..c2eff968 100644
--- a/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
+++ b/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
@@ -22,8 +22,7 @@ Connect only the references a component actually needs.
- Use `gpt:Image` with ordered `gpt:Reference` children when a new character/scene image must preserve
supplied identity or product facts.
-- Use `mimo:Preset` for a selected built-in voice or `mimo:VoiceDesign` for an English voice
- description. Either one produces the sample, once per person.
+- Use `mimo:VoiceDesign` with a written voice description. Generate the sample once per person.
- That sample is a reference on every take the person appears in, and the take speaks the Segment.
`generated-dependencies.md` holds the rule and what it costs: one generation carries the speech and
the picture, so the Segment's length and its picture's length are one number.
diff --git a/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md b/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md
index 22c22080..3304a090 100644
--- a/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md
+++ b/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md
@@ -7,7 +7,7 @@ ordered reveals and interpretations.
- Write one authoritative Script with Selections/Moments for the question, choice window, each reveal,
and the close.
-- Take the voice sample once with `mimo:Preset` or `mimo:VoiceDesign`. The reading is spoken by a
+- Take the voice sample once with `mimo:VoiceDesign`. The reading is spoken by a
take, and that take is the base under the whole Segment — the cards and the spread cover it, and
the speech and the picture stay one generation. `../craft/generated-dependencies.md` says why.
Cut the Segment to fit one generation.
diff --git a/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md b/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md
index 2b1428f8..625b6ac4 100644
--- a/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md
+++ b/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md
@@ -6,7 +6,7 @@ screen, product, hand, or proof changes.
## Author the SVML program
1. Write one narration Script Segment with Selections/Moments for every visual proof beat.
-2. Take the voice sample once, with `mimo:Preset` or `mimo:VoiceDesign`.
+2. Take the voice sample once with `mimo:VoiceDesign`.
3. The narration is spoken by a take, and that take is the base. It is under the whole Segment and
the B-roll covers it; the viewer sees the desk only where nothing is over it, and the speech and
the picture are one generation either way — `../craft/generated-dependencies.md` says why that
diff --git a/.agents/skills/hypit/references/runtime.md b/.agents/skills/hypit/references/runtime.md
index 38e7a526..50c1bbd3 100644
--- a/.agents/skills/hypit/references/runtime.md
+++ b/.agents/skills/hypit/references/runtime.md
@@ -45,7 +45,7 @@ gateway, so a typical profile looks like this:
"hypihub.<project>": {
"use": "@hypit/provider-hypihub",
"config": {
- "apiKey": { "store": "env", "key": "HYPIHUB_API_KEY" },
+ "apiKey": { "store": "os", "key": "hypihub.oauth" },
"defaultConcurrency": 20
}
}
@@ -53,9 +53,9 @@ gateway, so a typical profile looks like this:
`defaultConcurrency` is the total HypiHub pool shared by its model capabilities. Tune it to the
quota behind the key; image/video capabilities keep exact-model lanes while Gemini requests share
-one conservative lane. An explicit KIE
-profile remains valid when a project deliberately chooses `@hypit/provider-kie`, but it is not the
-default route.
+one conservative lane. Bind every paid capability HypiHub supports to this Endpoint by default,
+including MiMo VoiceDesign. Select KIE, Vertex, official MiMo or another BYOK Provider only when the
+author explicitly asks not to use HypiHub or explicitly selects that Provider.
An Author Source importing `@hypit/gemini` remains Provider-neutral. Bind those capabilities to
`@hypit/provider-hypihub` for HypiHub's upload-backed Gemini endpoint, or to
diff --git a/docs/guide/packages.md b/docs/guide/packages.md
index 74d304ac..bf7f8cee 100644
--- a/docs/guide/packages.md
+++ b/docs/guide/packages.md
@@ -90,7 +90,7 @@ specific Provider deployment.
@hypit/gpt-image GPT Image model family
@hypit/nano-banana Nano Banana model family
@hypit/seedream Seedream model family
-@hypit/mimo-tts three exact Xiaomi MiMo TTS models + author Surfaces
+@hypit/mimo-tts Xiaomi MiMo VoiceDesign model + author Surface
@hypit/estimate duration estimation
@hypit/speech shared speech products
@hypit/speech-evidence acoustic evidence products
@@ -131,7 +131,7 @@ never on exact-model packages or the CLI.
@hypit/provider-hyperframes-aws-lambda asynchronous distributed rendering
@hypit/provider-image-opencv-local local OpenCV Raster execution
@hypit/provider-media-aws-lambda synchronous AWS media execution
-@hypit/provider-xiaomi-mimo official Xiaomi MiMo TTS API
+@hypit/provider-xiaomi-mimo official Xiaomi MiMo VoiceDesign API
```
### Layer 6: Runtime
diff --git a/docs/guide/providers.md b/docs/guide/providers.md
index 1e2094a8..ca6b69ad 100644
--- a/docs/guide/providers.md
+++ b/docs/guide/providers.md
@@ -84,7 +84,7 @@ Look at existing Providers for reference:
- `packages/provider-hyperframes-local/` — local Chrome rendering
- `packages/provider-hyperframes-aws-lambda/` — asynchronous Step Functions/Lambda rendering
- `packages/provider-media-aws-lambda/` — synchronous Lambda media execution over the shared ffmpeg body
-- `packages/provider-xiaomi-mimo/` — immediate official TTS API without importing the MiMo model package
+- `packages/provider-xiaomi-mimo/` — immediate official VoiceDesign API without importing the MiMo model package
## 4. Write the activation descriptor
@@ -222,4 +222,4 @@ hypit doctor hypit.runtime.json
| `provider-hyperframes-aws-lambda` | Remote asynchronous job: Step Functions submission, polling and S3 streaming |
| `provider-image-opencv-local` | Local Python: bounded OpenCV/NumPy with locked Python environment |
| `provider-media-aws-lambda` | Remote synchronous Lambda: the same nine capabilities as local media |
-| `provider-xiaomi-mimo` | Remote immediate API: exact MiMo TTS requests to persisted audio Artifacts |
+| `provider-xiaomi-mimo` | Remote immediate API: exact MiMo VoiceDesign requests to persisted audio Artifacts |
diff --git a/docs/quickstart/run.md b/docs/quickstart/run.md
index bef5f1d2..afbe256e 100644
--- a/docs/quickstart/run.md
+++ b/docs/quickstart/run.md
@@ -213,7 +213,7 @@ variables referenced by the selected Runtime Profile:
|---|---|
| HypiHub OAuth | HypiHub paid generation and Gemini VLM; run `hypit auth login hypihub.default --runtime hypit.runtime.json` |
| `KIE_API_KEY` | Explicit KIE Provider only |
-| `MIMO_API_KEY` | Xiaomi MiMo TTS, only when that Endpoint is selected |
+| `MIMO_API_KEY` | Xiaomi MiMo VoiceDesign, only when the official Endpoint is explicitly selected |
Run only the lines for the Endpoints in your Profile. In macOS/Linux shells:
diff --git a/docs/zh/guide/packages.md b/docs/zh/guide/packages.md
index f7f11b64..a2fab318 100644
--- a/docs/zh/guide/packages.md
+++ b/docs/zh/guide/packages.md
@@ -83,7 +83,7 @@ Frontend;不存在一个认识全部语法的中央解析器。
@hypit/gpt-image GPT Image model family
@hypit/nano-banana Nano Banana model family
@hypit/seedream Seedream model family
-@hypit/mimo-tts 三个精确 Xiaomi MiMo TTS 模型及作者 Surface
+@hypit/mimo-tts Xiaomi MiMo VoiceDesign 模型及作者 Surface
@hypit/estimate duration estimation
@hypit/speech shared speech products
@hypit/speech-evidence acoustic evidence products
@@ -123,7 +123,7 @@ Frontend;不存在一个认识全部语法的中央解析器。
@hypit/provider-hyperframes-aws-lambda asynchronous distributed rendering
@hypit/provider-image-opencv-local 本地 OpenCV 光栅执行
@hypit/provider-media-aws-lambda synchronous AWS media execution
-@hypit/provider-xiaomi-mimo Xiaomi 官方 MiMo TTS API
+@hypit/provider-xiaomi-mimo Xiaomi 官方 MiMo VoiceDesign API
```
### Layer 6:Runtime
diff --git a/docs/zh/guide/providers.md b/docs/zh/guide/providers.md
index 43831dbc..a39539c0 100644
--- a/docs/zh/guide/providers.md
+++ b/docs/zh/guide/providers.md
@@ -81,7 +81,7 @@ export function createMyServiceProvider(options: {
- `packages/provider-hyperframes-local/` — 本地 Chrome 渲染
- `packages/provider-hyperframes-aws-lambda/` — 异步 Step Functions/Lambda 渲染
- `packages/provider-media-aws-lambda/` — 通过共享 ffmpeg 执行体完成同步 Lambda 媒体操作
-- `packages/provider-xiaomi-mimo/` — 不依赖 MiMo 模型包的官方即时 TTS API
+- `packages/provider-xiaomi-mimo/` — 不依赖 MiMo 模型包的官方即时 VoiceDesign API
## 4. 编写 activation 描述符
@@ -214,4 +214,4 @@ hypit doctor hypit.runtime.json
| `provider-hyperframes-aws-lambda` | 远程可恢复任务:确定性 Step Functions 提交、轮询与 S3 流式落库 |
| `provider-image-opencv-local` | 本地 Python:有界的 OpenCV/NumPy,配合锁定的 Python 环境 |
| `provider-media-aws-lambda` | 远程同步 Lambda:与本地媒体相同的九项能力 |
-| `provider-xiaomi-mimo` | 远程即时 API:把精确 MiMo TTS 请求落成持久化音频 Artifact |
+| `provider-xiaomi-mimo` | 远程即时 API:把精确 MiMo VoiceDesign 请求落成持久化音频 Artifact |
diff --git a/docs/zh/quickstart/run.md b/docs/zh/quickstart/run.md
index af158a24..4d0cb142 100644
--- a/docs/zh/quickstart/run.md
+++ b/docs/zh/quickstart/run.md
@@ -187,7 +187,7 @@ hypit paths
|---|---|
| HypiHub OAuth | HypiHub 付费生成与 Gemini VLM;运行 `hypit auth login hypihub.default --runtime hypit.runtime.json` 并在 https://hypit.ai 登录 |
| `KIE_API_KEY` | 仅在显式选择 KIE Provider 时使用 |
-| `MIMO_API_KEY` | Xiaomi MiMo TTS;只有选择该 Endpoint 时才需要 |
+| `MIMO_API_KEY` | Xiaomi MiMo VoiceDesign;只有明确选择官方 Endpoint 时才需要 |
只执行 Profile 中所选 Endpoint 对应的行。在 macOS/Linux Shell 中:
diff --git a/packages/mimo-tts/README.md b/packages/mimo-tts/README.md
index 64424a60..e4d73f20 100644
--- a/packages/mimo-tts/README.md
+++ b/packages/mimo-tts/README.md
@@ -1,15 +1,12 @@
# `@hypit/mimo-tts`
-Exact model contracts and author Surfaces for Xiaomi MiMo V2.5 speech synthesis.
+Exact model contract and author Surface for Xiaomi MiMo V2.5 VoiceDesign.
-The package owns the three distinct model shapes:
-
-- `mimo-v2.5-tts`: explicit built-in voice;
-- `mimo-v2.5-tts-voicedesign`: text-described voice;
-- `mimo-v2.5-tts-voiceclone`: one explicit audio sample.
+The package owns only `mimo-v2.5-tts-voicedesign`: exact speech text plus a
+natural-language voice description.
It contains no API URL, credential, retry, queue or Xiaomi wire encoding. Those belong to a Runtime
-Endpoint such as `@hypit/provider-xiaomi-mimo`. Every model returns the shared
+Endpoint such as `@hypit/provider-xiaomi-mimo`. The model returns the shared
`GeneratedAudioSet`; author Surfaces expose its primary member as an ordinary `BlobArtifact`.
The `speech` attribute is an ordinary `Text` edge attached through the exact model's `text` port at
execution time; the Frontend never copies Script words into a request draft.
@@ -19,17 +16,9 @@ execution time; the Frontend never copies Script words into a request draft.
```xml
<import as="mimo" from="@hypit/mimo-tts@1"/>
-<mimo:Preset id="narration" speech={story.segment.opening.speech} voice="Chloe">
- Warm, direct and conversational.
-</mimo:Preset>
-
<mimo:VoiceDesign id="designed" speech={story.segment.answer.speech}>
A clear young woman with a grounded, confident delivery.
</mimo:VoiceDesign>
-
-<mimo:VoiceClone id="cloned" speech={story.segment.payoff.speech} sample={presenter-voice}>
- Calm and restrained.
-</mimo:VoiceClone>
```
Official API reference: <https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5>
diff --git a/packages/mimo-tts/src/activation.ts b/packages/mimo-tts/src/activation.ts
index 2e4decbd..fd437f2f 100644
--- a/packages/mimo-tts/src/activation.ts
+++ b/packages/mimo-tts/src/activation.ts
@@ -1,8 +1,6 @@
import { createMarkupSurfaceHostFacet } from "@hypit/markup";
import {
- decodeMimoPresetSurface,
- decodeMimoVoiceCloneSurface,
decodeMimoVoiceDesignSurface,
mimoTtsComponent,
mimoTtsDefinition,
@@ -17,18 +15,10 @@ export const hypitPackage = {
components: [mimoTtsComponent],
hostFacets: [
mimoTtsDefinition.hostFacet,
- createMarkupSurfaceHostFacet({
- module: mimoTtsModuleRef,
- declaration: mimoTtsMarkupSurfaces.find((item) => item.name === "preset")!, handler: decodeMimoPresetSurface,
- }),
createMarkupSurfaceHostFacet({
module: mimoTtsModuleRef,
declaration: mimoTtsMarkupSurfaces.find((item) => item.name === "voiceDesign")!, handler: decodeMimoVoiceDesignSurface,
}),
- createMarkupSurfaceHostFacet({
- module: mimoTtsModuleRef,
- declaration: mimoTtsMarkupSurfaces.find((item) => item.name === "voiceClone")!, handler: decodeMimoVoiceCloneSurface,
- }),
],
};
diff --git a/packages/mimo-tts/src/index.ts b/packages/mimo-tts/src/index.ts
index 734081e0..e8091147 100644
--- a/packages/mimo-tts/src/index.ts
+++ b/packages/mimo-tts/src/index.ts
@@ -6,61 +6,28 @@ import { defineExactModelModule } from "@hypit/model-kit";
import { textTypes } from "@hypit/text";
export const mimoTtsModuleRef = { name: "@hypit/mimo-tts", version: "1" } as const;
-export const mimoTtsModels = [
- "mimo-v2.5-tts",
- "mimo-v2.5-tts-voicedesign",
- "mimo-v2.5-tts-voiceclone",
-] as const;
+export const mimoTtsModels = ["mimo-v2.5-tts-voicedesign"] as const;
export type MimoTtsModel = typeof mimoTtsModels[number];
-export const mimoPresetVoices = ["冰糖", "茉莉", "苏打", "白桦", "Mia", "Chloe", "Milo", "Dean"] as const;
-export type MimoPresetVoice = typeof mimoPresetVoices[number];
-
// Xiaomi documents no fixed character ceiling. Service-side limits stay service-side
// instead of becoming an invented model constraint in Author Source.
const spokenText = { kind: "text" } as const;
const instruction = { kind: "text" } as const;
function table(model: MimoTtsModel): GenerationPortTable {
- const common = [
- { name: "text", value: spokenText, minItems: 1, maxItems: 1 },
- ] as const;
- if (model === "mimo-v2.5-tts") {
- return sealGenerationPortTable({
- model, result: "audio",
- ports: [
- ...common,
- { name: "instruction", value: instruction, minItems: 0, maxItems: 1 },
- { name: "voice", value: { kind: "enum", values: [...mimoPresetVoices] }, minItems: 1, maxItems: 1 },
- ],
- requires: [],
- });
- }
- if (model === "mimo-v2.5-tts-voicedesign") {
- return sealGenerationPortTable({
- model, result: "audio",
- ports: [
- ...common,
- { name: "voiceDescription", value: instruction, minItems: 1, maxItems: 1 },
- ],
- requires: [],
- });
- }
return sealGenerationPortTable({
- model, result: "audio",
+ model,
+ result: "audio",
ports: [
- ...common,
- { name: "instruction", value: instruction, minItems: 0, maxItems: 1 },
- { name: "sample", value: { kind: "media", accepts: ["audio"] }, minItems: 1, maxItems: 1 },
+ { name: "text", value: spokenText, minItems: 1, maxItems: 1 },
+ { name: "voiceDescription", value: instruction, minItems: 1, maxItems: 1 },
],
requires: [],
});
}
export const mimoTtsPorts: Readonly<Record<MimoTtsModel, GenerationPortTable>> = {
- "mimo-v2.5-tts": table("mimo-v2.5-tts"),
"mimo-v2.5-tts-voicedesign": table("mimo-v2.5-tts-voicedesign"),
- "mimo-v2.5-tts-voiceclone": table("mimo-v2.5-tts-voiceclone"),
};
export function sealMimoTtsRequest(
@@ -79,16 +46,12 @@ export function sealMimoTtsRequestDraft(
const base = defineExactModelModule({
module: mimoTtsModuleRef,
- endpoints: ([
- ["preset", "mimo-v2.5-tts", "MimoPresetTtsRequest"],
- ["voiceDesign", "mimo-v2.5-tts-voicedesign", "MimoVoiceDesignTtsRequest"],
- ["voiceClone", "mimo-v2.5-tts-voiceclone", "MimoVoiceCloneTtsRequest"],
- ] as const).map(([key, model, requestTypeName]) => ({
- key,
- requestTypeName,
- producerName: `request-${model}`,
- ports: mimoTtsPorts[model],
- })),
+ endpoints: [{
+ key: "voiceDesign",
+ requestTypeName: "MimoVoiceDesignTtsRequest",
+ producerName: "request-mimo-v2.5-tts-voicedesign",
+ ports: mimoTtsPorts["mimo-v2.5-tts-voicedesign"],
+ }],
});
export const mimoTtsEndpoints = base.endpoints;
@@ -115,95 +78,27 @@ const mimoAudioPort: readonly SurfacePortVocabulary[] = [{
summary: "The synthesized speech, addressed as `<id>.audio`.",
}];
-export const mimoTtsMarkupSurfaces = [
- {
- name: "preset", tag: "Preset", mode: "structured",
- outputs: [mimoTtsEndpoints.preset.draftType],
- vocabulary: {
- summary: "Speaks a Text with one of the built-in MiMo voices.",
- attributes: [
- ...mimoSpokenAttributes,
- {
- name: "voice",
- kind: "literal",
- required: true,
- summary: "The built-in voice that reads the speech.",
- values: mimoPresetVoices,
- },
- ],
- ports: mimoAudioPort,
- text: "The element's own text is an optional delivery instruction; leaving it empty sends no instruction.",
- example: `<mimo:Preset id="narration" speech={story.segment.opening.speech} voice="Chloe">
- Warm, direct and conversational.
-</mimo:Preset>`,
- notes: [
- "The element accepts no child elements; only its text is read.",
- "`speech` stays an ordinary Text edge attached at execution time, so the Frontend copies no Script words into the request draft.",
- ],
- },
- },
- {
- name: "voiceDesign", tag: "VoiceDesign", mode: "structured",
- outputs: [mimoTtsEndpoints.voiceDesign.draftType],
- vocabulary: {
- summary: "Speaks a Text with a voice the element describes in words rather than names.",
- attributes: mimoSpokenAttributes,
- ports: mimoAudioPort,
- text: "The element's own text is the voice description and is required.",
- example: `<mimo:VoiceDesign id="designed" speech={story.segment.answer.speech}>
+export const mimoTtsMarkupSurfaces = [{
+ name: "voiceDesign", tag: "VoiceDesign", mode: "structured",
+ outputs: [mimoTtsEndpoints.voiceDesign.draftType],
+ vocabulary: {
+ summary: "Speaks a Text with a voice described in natural language.",
+ attributes: mimoSpokenAttributes,
+ ports: mimoAudioPort,
+ text: "The element's own text is the voice description and is required.",
+ example: `<mimo:VoiceDesign id="designed" speech={story.segment.answer.speech}>
A clear young woman with a grounded, confident delivery.
</mimo:VoiceDesign>`,
- notes: [
- "The element accepts no child elements; only its text is read.",
- "An empty body is refused, because this model has no voice to fall back on.",
- ],
- },
- },
- {
- name: "voiceClone", tag: "VoiceClone", mode: "structured",
- outputs: [
- mimoTtsEndpoints.voiceClone.draftType,
- ...Object.values(mimoTtsEndpoints.voiceClone.mediaBindings).map((binding) => binding.type),
+ notes: [
+ "The element accepts no child elements; only its text is read.",
+ "An empty body is refused, because this model has no voice to fall back on.",
],
- vocabulary: {
- summary: "Speaks a Text with the voice heard in one audio Artifact.",
- attributes: [
- ...mimoSpokenAttributes,
- {
- name: "sample",
- kind: "reference",
- required: true,
- summary: "The audio Artifact whose voice the model reproduces.",
- accepts: [artifactTypes.blob],
- },
- ],
- ports: mimoAudioPort,
- text: "The element's own text is an optional delivery instruction; leaving it empty sends no instruction.",
- example: `<mimo:VoiceClone id="cloned" speech={story.segment.payoff.speech} sample={presenter.audio}>
- Calm and restrained.
-</mimo:VoiceClone>`,
- notes: [
- "The element accepts no child elements; only its text is read.",
- "An authored `sample` whose media type is not audio is refused before any Need exists.",
- ],
- },
},
-] as const;
-
-export const mimoTtsManifest = {
- ...base.manifest,
-} as const;
+}] as const;
+export const mimoTtsManifest = { ...base.manifest } as const;
export const mimoTtsComponent = base.component;
-
-export const mimoTtsDefinition = {
- ...base,
- manifest: mimoTtsManifest,
-};
+export const mimoTtsDefinition = { ...base, manifest: mimoTtsManifest };
export { createMimoTtsAudioFragment } from "./fragment.js";
-export {
- decodeMimoPresetSurface,
- decodeMimoVoiceCloneSurface,
- decodeMimoVoiceDesignSurface,
-} from "./surface.js";
+export { decodeMimoVoiceDesignSurface } from "./surface.js";
diff --git a/packages/mimo-tts/src/surface.ts b/packages/mimo-tts/src/surface.ts
index 0cf7766c..22c80050 100644
--- a/packages/mimo-tts/src/surface.ts
+++ b/packages/mimo-tts/src/surface.ts
@@ -1,12 +1,6 @@
-import { artifactTypes } from "@hypit/artifact";
-import {
- generationPort,
- sealGenerationMediaBinding,
-} from "@hypit/generation";
-import type { GenerationMediaPort, GenerationPortValue } from "@hypit/generation";
-import { exactModelMediaInputNames, exactModelTextInputName } from "@hypit/model-kit";
-import type { ExactModelMediaInput, ExactModelTextInput } from "@hypit/model-kit";
import type { CanonicalValue } from "@hypit/protocol";
+import { exactModelTextInputName } from "@hypit/model-kit";
+import type { ExactModelTextInput } from "@hypit/model-kit";
import { textTypes, verifyText } from "@hypit/text";
import type {
StructuredElement,
@@ -16,23 +10,17 @@ import type {
} from "@hypit/markup";
import { createMimoTtsAudioFragment } from "./fragment.js";
-import {
- mimoPresetVoices,
- mimoTtsEndpoints,
- sealMimoTtsRequestDraft,
-} from "./index.js";
-import type { MimoPresetVoice, MimoTtsModel } from "./index.js";
+import { mimoTtsEndpoints, sealMimoTtsRequestDraft } from "./index.js";
function sameType(left: SurfaceResolvedReference["type"], right: SurfaceResolvedReference["type"]): boolean {
return left.module.name === right.module.name && left.module.version === right.module.version && left.name === right.name;
}
-function attributes(element: StructuredElement, required: readonly string[], optional: readonly string[] = []): void {
- const allowed = new Set([...required, ...optional]);
+function attributes(element: StructuredElement, required: readonly string[]): void {
+ const allowed = new Set(required);
const unknown = Object.keys(element.attributes).filter((name) => !allowed.has(name));
if (unknown.length > 0 || required.some((name) => element.attributes[name] === undefined)) {
- throw new Error(`${element.name} requires ${required.join(", ")}`
- + (optional.length === 0 ? "" : `; optional: ${optional.join(", ")}`));
+ throw new Error(`${element.name} requires ${required.join(", ")}`);
}
}
@@ -64,9 +52,7 @@ function resolved(
}
function speechText(reference: SurfaceResolvedReference, subject: string): SurfaceResolvedReference {
- if (!sameType(reference.type, textTypes.text)) {
- throw new Error(`${subject} must reference Text`);
- }
+ if (!sameType(reference.type, textTypes.text)) throw new Error(`${subject} must reference Text`);
const value = reference.record?.value;
if (value !== undefined) {
if (value.kind !== "inline") throw new Error(`${subject} has an invalid authored Text value`);
@@ -75,18 +61,7 @@ function speechText(reference: SurfaceResolvedReference, subject: string): Surfa
return reference;
}
-function sample(reference: SurfaceResolvedReference, subject: string): SurfaceResolvedReference {
- if (!sameType(reference.type, artifactTypes.blob)) {
- throw new Error(`${subject} must reference an audio BlobArtifact`);
- }
- const value = reference.record?.value;
- if (value !== undefined && (value.kind !== "blob" || !value.mediaType.startsWith("audio/"))) {
- throw new Error(`${subject} must be audio media`);
- }
- return reference;
-}
-
-function body(element: StructuredElement, required: boolean): string | undefined {
+function body(element: StructuredElement): string {
if (element.children.some((child) => child.kind === "element")) {
throw new Error(`${element.name} accepts instruction text only`);
}
@@ -97,117 +72,38 @@ function body(element: StructuredElement, required: boolean): string | undefined
const indents = lines.filter((line) => line.trim()).map((line) => /^\s*/u.exec(line)?.[0].length ?? 0);
const indent = indents.length === 0 ? 0 : Math.min(...indents);
const value = lines.map((line) => line.slice(indent).trimEnd()).join("\n").trim();
- if (value.length === 0) {
- if (required) throw new Error(`${element.name} requires a voice description in its body`);
- return undefined;
- }
+ if (value.length === 0) throw new Error(`${element.name} requires a voice description in its body`);
return value;
}
-function output(
- element: StructuredElement,
- endpoint: (typeof mimoTtsEndpoints)[keyof typeof mimoTtsEndpoints],
- draft: ReturnType<typeof sealMimoTtsRequestDraft>,
- text: readonly { readonly input: ExactModelTextInput; readonly source: SurfaceResolvedReference }[],
- media: readonly { readonly input: ExactModelMediaInput; readonly source: SurfaceResolvedReference }[] = [],
-) {
+export const decodeMimoVoiceDesignSurface: StructuredSurfaceHandler = ({ element, resolveReference }) => {
+ attributes(element, ["id", "speech"]);
const id = stringAttribute(element, "id");
+ const speech = speechText(resolved(element, "speech", resolveReference), `${element.name}.speech`);
+ const endpoint = mimoTtsEndpoints.voiceDesign;
const draftId = `${id}.draft`;
- const records: Array<{
- readonly id: string;
- readonly type: SurfaceResolvedReference["type"];
- readonly value: { readonly kind: "inline"; readonly value: CanonicalValue };
- readonly range: StructuredElement["range"];
- }> = [{
- id: draftId,
- type: endpoint.draftType,
- value: { kind: "inline", value: draft as unknown as CanonicalValue },
- range: element.range,
- }];
- const inputs: Record<string, SurfaceResolvedReference["ref"] | { readonly kind: "record"; readonly id: string }> = {
- draft: { kind: "record", id: draftId },
- };
- for (const item of text) inputs[exactModelTextInputName(item.input.name)] = item.source.ref;
- for (const item of media) {
- const binding = endpoint.mediaBindings[item.input.port];
- if (binding === undefined) throw new Error(`${endpoint.ports.model} has no media port ${item.input.port}`);
- const port = generationPort(endpoint.ports, item.input.port);
- if (port.value.kind !== "media") throw new Error(`${endpoint.ports.model} port ${item.input.port} is not media`);
- const names = exactModelMediaInputNames(item.input.name);
- const bindingId = `${id}.${item.input.name}.binding`;
- records.push({
- id: bindingId,
- type: binding.type,
- value: {
- kind: "inline",
- value: sealGenerationMediaBinding(port as GenerationMediaPort, { role: "audio" }) as unknown as CanonicalValue,
- },
- range: element.range,
- });
- inputs[names.binding] = { kind: "record", id: bindingId };
- inputs[names.artifact] = item.source.ref;
- }
- const fragment = createMimoTtsAudioFragment(
- endpoint,
- media.map((item) => item.input),
- text.map((item) => item.input),
- );
+ const draft = sealMimoTtsRequestDraft("mimo-v2.5-tts-voicedesign", {
+ voiceDescription: [body(element)],
+ });
+ const textInput: ExactModelTextInput = { name: "speech", port: "text" };
+ const fragment = createMimoTtsAudioFragment(endpoint, [], [textInput]);
return {
- records,
+ records: [{
+ id: draftId,
+ type: endpoint.draftType,
+ value: { kind: "inline", value: draft as unknown as CanonicalValue },
+ range: element.range,
+ }],
components: [{
id,
fragment: fragment.id,
- inputs,
+ inputs: {
+ draft: { kind: "record", id: draftId },
+ [exactModelTextInputName(textInput.name)]: speech.ref,
+ },
outputs: { audio: `${id}.audio` },
range: element.range,
}],
fragments: [fragment],
};
-}
-
-function speechInput(
- element: StructuredElement,
- resolveReference: (path: string) => SurfaceResolvedReference | undefined,
-) {
- return {
- input: { name: "speech", port: "text" },
- source: speechText(resolved(element, "speech", resolveReference), `${element.name}.speech`),
- } as const;
-}
-
-export const decodeMimoPresetSurface: StructuredSurfaceHandler = ({ element, resolveReference }) => {
- attributes(element, ["id", "speech", "voice"]);
- const voice = stringAttribute(element, "voice") as MimoPresetVoice;
- if (!mimoPresetVoices.includes(voice)) throw new Error(`${element.name}.voice is not a MiMo preset voice`);
- const instruction = body(element, false);
- const ports: Record<string, readonly GenerationPortValue[]> = { voice: [voice] };
- if (instruction !== undefined) ports.instruction = [instruction];
- return output(
- element,
- mimoTtsEndpoints.preset,
- sealMimoTtsRequestDraft("mimo-v2.5-tts", ports),
- [speechInput(element, resolveReference)],
- );
-};
-
-export const decodeMimoVoiceDesignSurface: StructuredSurfaceHandler = ({ element, resolveReference }) => {
- attributes(element, ["id", "speech"]);
- return output(element, mimoTtsEndpoints.voiceDesign, sealMimoTtsRequestDraft("mimo-v2.5-tts-voicedesign", {
- voiceDescription: [body(element, true)!],
- }), [speechInput(element, resolveReference)]);
-};
-
-export const decodeMimoVoiceCloneSurface: StructuredSurfaceHandler = ({ element, resolveReference }) => {
- attributes(element, ["id", "speech", "sample"]);
- const instruction = body(element, false);
- const source = sample(resolved(element, "sample", resolveReference), `${element.name}.sample`);
- const ports: Record<string, readonly GenerationPortValue[]> = {};
- if (instruction !== undefined) ports.instruction = [instruction];
- return output(
- element,
- mimoTtsEndpoints.voiceClone,
- sealMimoTtsRequestDraft("mimo-v2.5-tts-voiceclone", ports),
- [speechInput(element, resolveReference)],
- [{ input: { name: "sample", port: "sample" }, source }],
- );
};
diff --git a/packages/mimo-tts/test/mimo-tts.test.ts b/packages/mimo-tts/test/mimo-tts.test.ts
index 8e753923..9de58898 100644
--- a/packages/mimo-tts/test/mimo-tts.test.ts
+++ b/packages/mimo-tts/test/mimo-tts.test.ts
@@ -1,20 +1,17 @@
import assert from "node:assert/strict";
import test from "node:test";
-import { fixtureDigest } from "../../../test/fixture-digest.js";
-import { artifactTypes } from "@hypit/artifact";
import { generationProducers, generationTypes } from "@hypit/generation";
-import { sealText, textTypes } from "@hypit/text";
import { parseStructuredElement } from "@hypit/markup";
import type { SurfaceResolvedReference } from "@hypit/markup";
+import { sealText, textTypes } from "@hypit/text";
import mimoNodePackage from "../src/activation.js";
import {
- decodeMimoPresetSurface,
- decodeMimoVoiceCloneSurface,
decodeMimoVoiceDesignSurface,
mimoTtsEndpoints,
mimoTtsMarkupSurfaces,
+ mimoTtsModels,
mimoTtsPorts,
sealMimoTtsRequest,
} from "../src/index.js";
@@ -23,106 +20,60 @@ function parsed(source: string) {
return parseStructuredElement({ name: "mimo.svml", text: source }, 0).element;
}
-function authored(path: string, type: SurfaceResolvedReference["type"], value: unknown): SurfaceResolvedReference {
- return {
- path,
- ref: { kind: "record", id: path },
- type,
- record: {
- id: path,
- type,
- value: type.name === artifactTypes.blob.name
- ? value as never
- : { kind: "inline", value: value as never },
- },
- };
-}
-
const speech = sealText("Exact authored words stay exact.");
-const sample = { kind: "blob" as const, digest: fixtureDigest("voice-sample"), size: 4, mediaType: "audio/wav" };
-const refs = new Map<string, SurfaceResolvedReference>([
- ["story.segment.opening.speech", authored("story.segment.opening.speech", textTypes.text, speech)],
- ["voice", authored("voice", artifactTypes.blob, sample)],
-]);
+const reference: SurfaceResolvedReference = {
+ path: "story.segment.opening.speech",
+ ref: { kind: "record", id: "story.segment.opening.speech" },
+ type: textTypes.text,
+ record: {
+ id: "story.segment.opening.speech",
+ type: textTypes.text,
+ value: { kind: "inline", value: speech },
+ },
+};
const context = (source: string) => ({
sourceName: "mimo.svml",
element: parsed(source),
- resolveReference: (path: string) => refs.get(path),
+ resolveReference: (path: string) => path === reference.path ? reference : undefined,
resolveAsset: () => { throw new Error("no asset"); },
});
-test("MiMo declares three audio models without Provider facts", () => {
- assert.deepEqual(Object.values(mimoTtsPorts).map((ports) => ports.result), ["audio", "audio", "audio"]);
- assert.deepEqual(Object.values(mimoTtsEndpoints).map((endpoint) => endpoint.returns), [
- generationTypes.audioSet,
- generationTypes.audioSet,
- generationTypes.audioSet,
- ]);
+test("MiMo declares only the VoiceDesign audio model without Provider facts", () => {
+ assert.deepEqual(mimoTtsModels, ["mimo-v2.5-tts-voicedesign"]);
+ assert.deepEqual(Object.values(mimoTtsPorts).map((ports) => ports.result), ["audio"]);
+ assert.deepEqual(Object.values(mimoTtsEndpoints).map((endpoint) => endpoint.returns), [generationTypes.audioSet]);
assert.equal(JSON.stringify(mimoTtsPorts).includes("xiaomimimo.com"), false);
- assert.equal(mimoTtsPorts["mimo-v2.5-tts"].ports.find((port) => port.name === "text")?.value.kind, "text");
- assert.equal("maxChars" in mimoTtsPorts["mimo-v2.5-tts"].ports[0]!.value, false);
assert.throws(() => sealMimoTtsRequest("mimo-v2.5-tts-voicedesign", {
text: ["Do not rewrite me."],
}), /voiceDescription is required/u);
});
-test("one installed author package contributes all three Surfaces without a Runtime Provider", () => {
+test("the installed author package contributes only VoiceDesign", () => {
assert.equal(mimoNodePackage.format, "hypit.node-package@1");
assert.equal(mimoNodePackage.modules[0]?.manifest.version, "1");
- assert.deepEqual(mimoTtsMarkupSurfaces.map((surface) => surface.name),
- ["preset", "voiceDesign", "voiceClone"]);
+ assert.deepEqual(mimoTtsMarkupSurfaces.map((surface) => surface.name), ["voiceDesign"]);
assert.equal(JSON.stringify(mimoNodePackage).includes("MIMO_API_KEY"), false);
});
-test("the three author Surfaces are separate components with one ordinary audio output", async () => {
- const results = await Promise.all([
- decodeMimoPresetSurface(context(`<mimo:Preset id="preset" speech={story.segment.opening.speech} voice="Chloe">
- Warm, restrained delivery.
- </mimo:Preset>`)),
- decodeMimoVoiceDesignSurface(context(`<mimo:VoiceDesign id="designed" speech={story.segment.opening.speech}>
- A clear, confident young woman with a grounded conversational tone.
- </mimo:VoiceDesign>`)),
- decodeMimoVoiceCloneSurface(context(`<mimo:VoiceClone id="cloned" speech={story.segment.opening.speech} sample={voice}>
- Calm and direct.
- </mimo:VoiceClone>`)),
+test("VoiceDesign produces one ordinary audio output", async () => {
+ const result = await decodeMimoVoiceDesignSurface(context(`<mimo:VoiceDesign id="designed" speech={story.segment.opening.speech}>
+ A clear, confident young woman with a grounded conversational tone.
+ </mimo:VoiceDesign>`));
+ assert.equal(result.components.length, 1);
+ assert.deepEqual(Object.keys(result.components[0]!.outputs), ["audio"]);
+ assert.deepEqual(result.fragments[0]!.operations.map((operation) => operation.producer.name), [
+ "bind-request-mimo-v2.5-tts-voicedesign-text-text",
+ "finalize-request-mimo-v2.5-tts-voicedesign",
+ "request-mimo-v2.5-tts-voicedesign",
+ generationProducers.primaryAudio.name,
]);
- for (const [index, result] of results.entries()) {
- assert.equal(result.components.length, 1);
- assert.deepEqual(Object.keys(result.components[0]!.outputs), ["audio"]);
- assert.deepEqual(result.fragments[0]!.operations.map((operation) => operation.producer.name), index === 2
- ? [
- "bind-request-mimo-v2.5-tts-voiceclone-text-text",
- "bind-request-mimo-v2.5-tts-voiceclone-sample",
- "finalize-request-mimo-v2.5-tts-voiceclone",
- "request-mimo-v2.5-tts-voiceclone",
- generationProducers.primaryAudio.name,
- ]
- : [
- index === 0
- ? "bind-request-mimo-v2.5-tts-text-text"
- : "bind-request-mimo-v2.5-tts-voicedesign-text-text",
- index === 0 ? "finalize-request-mimo-v2.5-tts" : "finalize-request-mimo-v2.5-tts-voicedesign",
- index === 0 ? "request-mimo-v2.5-tts" : "request-mimo-v2.5-tts-voicedesign",
- generationProducers.primaryAudio.name,
- ]);
- assert.equal(result.records[0]!.value.kind, "inline");
- const request = result.records[0]!.value.kind === "inline"
- ? result.records[0]!.value.value as Record<string, unknown> : {};
- assert.equal((request.ports as Record<string, unknown[]>).text, undefined);
- assert.deepEqual(result.components[0]!.inputs["speech:text"], {
- kind: "record",
- id: "story.segment.opening.speech",
- });
- assert.equal(JSON.stringify(request).includes("optimize_text_preview"), false);
- }
-});
-
-test("voice clone refuses a non-audio sample before any Need exists", async () => {
- const wrong = { ...sample, mediaType: "video/mp4" };
- const invalid = new Map(refs);
- invalid.set("voice", authored("voice", artifactTypes.blob, wrong));
- assert.throws(() => decodeMimoVoiceCloneSurface({
- ...context('<mimo:VoiceClone id="bad" speech={story.segment.opening.speech} sample={voice}/>'),
- resolveReference: (path) => invalid.get(path),
- }), /must be audio/u);
+ assert.equal(result.records[0]!.value.kind, "inline");
+ const request = result.records[0]!.value.kind === "inline"
+ ? result.records[0]!.value.value as Record<string, unknown> : {};
+ assert.equal((request.ports as Record<string, unknown[]>).text, undefined);
+ assert.deepEqual(result.components[0]!.inputs["speech:text"], {
+ kind: "record",
+ id: "story.segment.opening.speech",
+ });
+ assert.equal(JSON.stringify(request).includes("optimize_text_preview"), false);
});
diff --git a/packages/provider-hypihub/README.md b/packages/provider-hypihub/README.md
index 67c45ebd..ea9debf2 100644
--- a/packages/provider-hypihub/README.md
+++ b/packages/provider-hypihub/README.md
@@ -40,7 +40,5 @@ Artifacts are uploaded automatically through `POST /v1/files`, then their return
URLs are used in image and video requests. Uploads are deduplicated by Artifact digest within one
Runtime operation. Embedded callers may override that transport with `publicAssetUrl`.
-HypiHub audio capabilities are disabled by default because a HypiHub OAuth grant may not include the MiMo
-audio models. Set `audio: true` only when that key explicitly has them enabled. The usual setup keeps
-official `@hypit/provider-xiaomi-mimo` as the audio endpoint, so one Runtime uses HypiHub for
-image/video and official MiMo for audio.
+HypiHub exposes MiMo VoiceDesign by default. Set `audio: false` only when the user explicitly selects
+another VoiceDesign Provider. Hypit does not expose MiMo preset-voice or voice-cloning models.
diff --git a/packages/provider-hypihub/src/provider.ts b/packages/provider-hypihub/src/provider.ts
index 7933d26b..c771b33d 100644
--- a/packages/provider-hypihub/src/provider.ts
+++ b/packages/provider-hypihub/src/provider.ts
@@ -21,7 +21,7 @@ export type CreateHypiHubProviderOptions = {
readonly defaultConcurrency?: number;
readonly pollIntervalMs?: number;
readonly requestTimeoutMs?: number;
- /** Expose HypiHub's MiMo audio capabilities. Disable when official MiMo owns audio. */
+ /** Expose HypiHub VoiceDesign. Defaults to enabled; set false only for an explicit alternate Provider. */
readonly audio?: boolean;
readonly fetch?: typeof globalThis.fetch;
/** Overrides the default POST /v1/files upload for referenced artifacts. */
@@ -255,10 +255,7 @@ export function createHypiHubProvider(options: CreateHypiHubProviderOptions = {}
credentials: { apiKey: options.apiKey ?? credentialRef("os", "hypihub.oauth") }, credentialInputs: { apiKey: { label: "HypiHub login" } }, defaultConcurrency: options.defaultConcurrency ?? 10,
capabilities: [
...hypiHubRoutes
- // HypiHub OAuth grants do not necessarily include the MiMo audio models. Keep
- // official Xiaomi MiMo as the safe default; opting into HypiHub audio is
- // an explicit Runtime decision for a key that actually has those models.
- .filter((route) => options.audio === true || route.media !== "audio")
+ .filter((route) => options.audio !== false || route.media !== "audio")
.map((route) => route.media === "audio"
? { capability: route.capability, returns: route.returns, lifecycle: "immediate" as const, handler: audioEndpoint, lane: route.capability.name }
: { capability: route.capability, returns: route.returns, lifecycle: "asynchronous" as const, endpoint: asyncEndpoint, lane: route.capability.name }),
diff --git a/packages/provider-hypihub/test/provider.test.ts b/packages/provider-hypihub/test/provider.test.ts
index d103bc9a..e640c986 100644
--- a/packages/provider-hypihub/test/provider.test.ts
+++ b/packages/provider-hypihub/test/provider.test.ts
@@ -30,7 +30,7 @@ async function endpointFor(request: Need, fetch: typeof globalThis.fetch): Promi
return resolution.registration.endpoint;
}
-test("HypiHub keeps MiMo VoiceDesign audio opt-in so official MiMo can own the default audio routes", async () => {
+test("HypiHub exposes VoiceDesign by default and permits an explicit alternate audio Provider", async () => {
const registry = new EndpointRegistry();
await createHypiHubProvider({ fetch: async () => { throw new Error("audio must not call fetch"); } }).install(registry);
assert.equal(registry.resolve({
@@ -39,17 +39,17 @@ test("HypiHub keeps MiMo VoiceDesign audio opt-in so official MiMo can own the d
returns: mimoTtsEndpoints.voiceDesign.returns,
constraints: { ports: {} },
result: "record:hypihub-audio-default",
- }).status, "missing");
+ }).status, "resolved");
- const optedIn = new EndpointRegistry();
- await createHypiHubProvider({ audio: true, fetch: async () => { throw new Error("not reached"); } }).install(optedIn);
- assert.equal(optedIn.resolve({
+ const optedOut = new EndpointRegistry();
+ await createHypiHubProvider({ audio: false, fetch: async () => { throw new Error("not reached"); } }).install(optedOut);
+ assert.equal(optedOut.resolve({
id: "need:hypihub-audio-opt-in",
capability: mimoTtsEndpoints.voiceDesign.capability,
returns: mimoTtsEndpoints.voiceDesign.returns,
constraints: { ports: {} },
result: "record:hypihub-audio-opt-in",
- }).status, "resolved");
+ }).status, "missing");
});
test("HypiHub uploads referenced Artifacts once, submits their HTTPS URLs, and persists the result", async () => {
diff --git a/packages/provider-xiaomi-mimo/README.md b/packages/provider-xiaomi-mimo/README.md
index f1def4c1..cf1ea4b5 100644
--- a/packages/provider-xiaomi-mimo/README.md
+++ b/packages/provider-xiaomi-mimo/README.md
@@ -1,11 +1,10 @@
# `@hypit/provider-xiaomi-mimo`
-Immediate Runtime Endpoint for Xiaomi's official MiMo V2.5 TTS API.
+Immediate Runtime Endpoint for Xiaomi's official MiMo V2.5 VoiceDesign API.
This package owns the `chat/completions` wire shape, `api-key` credential, timeout, response bounds,
-voice-sample data URI conversion and ArtifactStore ingestion. It does not import
-`@hypit/mimo-tts`: capabilities and model port names are bound as versioned data, keeping the
-three exact model contracts independent from this particular service.
+and ArtifactStore ingestion. It does not import `@hypit/mimo-tts`: the VoiceDesign capability and
+port names are bound as versioned data, keeping the exact model contract independent from this service.
Runtime Profile example:
diff --git a/packages/provider-xiaomi-mimo/src/activation.ts b/packages/provider-xiaomi-mimo/src/activation.ts
index 1661e63c..ec71b2a4 100644
--- a/packages/provider-xiaomi-mimo/src/activation.ts
+++ b/packages/provider-xiaomi-mimo/src/activation.ts
@@ -16,7 +16,7 @@ const adapter = createRuntimeEndpointAdapterFacet({
const config = runtimeConfigObject(context.config, "Xiaomi MiMo");
runtimeConfigExact(config, [
"apiBaseUrl", "apiKey", "defaultConcurrency", "requestTimeoutMs",
- "maxResponseBytes", "maxVoiceSampleBase64Bytes",
+ "maxResponseBytes",
], "Xiaomi MiMo");
const apiBaseUrl = runtimeConfigString(config.apiBaseUrl, "Xiaomi MiMo apiBaseUrl");
if (apiBaseUrl !== undefined) {
@@ -30,10 +30,6 @@ const adapter = createRuntimeEndpointAdapterFacet({
const defaultConcurrency = runtimeConfigPositiveInteger(config.defaultConcurrency, "Xiaomi MiMo defaultConcurrency");
const requestTimeoutMs = runtimeConfigPositiveInteger(config.requestTimeoutMs, "Xiaomi MiMo requestTimeoutMs");
const maxResponseBytes = runtimeConfigPositiveInteger(config.maxResponseBytes, "Xiaomi MiMo maxResponseBytes");
- const maxVoiceSampleBase64Bytes = runtimeConfigPositiveInteger(
- config.maxVoiceSampleBase64Bytes,
- "Xiaomi MiMo maxVoiceSampleBase64Bytes",
- );
return {
endpoint: createXiaomiMimoProvider({
instance: context.instance,
@@ -43,7 +39,6 @@ const adapter = createRuntimeEndpointAdapterFacet({
...(defaultConcurrency === undefined ? {} : { defaultConcurrency }),
...(requestTimeoutMs === undefined ? {} : { requestTimeoutMs }),
...(maxResponseBytes === undefined ? {} : { maxResponseBytes }),
- ...(maxVoiceSampleBase64Bytes === undefined ? {} : { maxVoiceSampleBase64Bytes }),
}),
};
},
diff --git a/packages/provider-xiaomi-mimo/src/provider.ts b/packages/provider-xiaomi-mimo/src/provider.ts
index d97076a0..cb0e5849 100644
--- a/packages/provider-xiaomi-mimo/src/provider.ts
+++ b/packages/provider-xiaomi-mimo/src/provider.ts
@@ -4,7 +4,7 @@ import {
generationTypes,
sealGeneratedAudioSet,
} from "@hypit/generation";
-import type { GenerationMediaValue, GenerationRequest } from "@hypit/generation";
+import type { GenerationRequest } from "@hypit/generation";
import { canonicalize } from "@hypit/protocol";
import type { CanonicalValue, CapabilityRef } from "@hypit/protocol";
import { credentialRef } from "@hypit/runtime";
@@ -12,11 +12,7 @@ import type { CredentialRef } from "@hypit/runtime";
export const xiaomiMimoProviderModuleRef = { name: "@hypit/provider-xiaomi-mimo", version: "1" } as const;
const mimoModelModule = { name: "@hypit/mimo-tts", version: "1" } as const;
-const modelNames = [
- "mimo-v2.5-tts",
- "mimo-v2.5-tts-voicedesign",
- "mimo-v2.5-tts-voiceclone",
-] as const;
+const modelNames = ["mimo-v2.5-tts-voicedesign"] as const;
type Model = typeof modelNames[number];
const capabilities = Object.fromEntries(modelNames.map((name) => [name, {
@@ -34,7 +30,6 @@ export type CreateXiaomiMimoProviderOptions = {
readonly defaultConcurrency?: number;
readonly requestTimeoutMs?: number;
readonly maxResponseBytes?: number;
- readonly maxVoiceSampleBase64Bytes?: number;
readonly fetch?: Fetch;
};
@@ -57,11 +52,7 @@ function normalizeBaseUrl(value: string): string {
function request(value: CanonicalValue, model: Model): GenerationRequest {
const result = value as unknown as GenerationRequest;
assert(result.ports !== null && typeof result.ports === "object", "Xiaomi MiMo request has no ports");
- const allowed = model === "mimo-v2.5-tts"
- ? new Set(["text", "instruction", "voice"])
- : model === "mimo-v2.5-tts-voicedesign"
- ? new Set(["text", "voiceDescription"])
- : new Set(["text", "instruction", "sample"]);
+ const allowed = new Set(["text", "voiceDescription"]);
assert(Object.keys(result.ports).every((name) => allowed.has(name)),
`${model} request contains an unsupported port`);
return result;
@@ -83,32 +74,6 @@ function credential(context: EndpointInvocationContext): string {
return value;
}
-async function readVoiceSample(
- context: EndpointInvocationContext,
- req: GenerationRequest,
- maxBase64Bytes: number,
-): Promise<string> {
- const values = req.ports.sample;
- assert(values?.length === 1, "MiMo voice clone requires exactly one sample");
- const value = values[0] as GenerationMediaValue;
- assert(value.role === "audio", "MiMo voice clone sample must be audio");
- const supported = new Set(["audio/mpeg", "audio/mp3", "audio/wav", "audio/x-wav"]);
- assert(supported.has(value.artifact.mediaType), "Xiaomi MiMo accepts only MP3 or WAV voice samples");
- const encodedSize = 4 * Math.ceil(value.artifact.size / 3);
- assert(encodedSize <= maxBase64Bytes,
- `MiMo voice sample exceeds the configured ${maxBase64Bytes}-byte Base64 limit`);
- const bytes = await context.artifacts.get(value.artifact.digest);
- assert(bytes !== undefined, `MiMo voice sample ${value.artifact.digest} is unavailable`);
- assert(bytes.byteLength === value.artifact.size, "MiMo voice sample size differs from its BlobRef");
- const mediaType = value.artifact.mediaType === "audio/x-wav"
- ? "audio/wav"
- : value.artifact.mediaType === "audio/mp3" ? "audio/mpeg" : value.artifact.mediaType;
- const encoded = Buffer.from(bytes).toString("base64");
- assert(Buffer.byteLength(encoded, "utf8") <= maxBase64Bytes,
- `MiMo voice sample exceeds the configured ${maxBase64Bytes}-byte Base64 limit`);
- return `data:${mediaType};base64,${encoded}`;
-}
-
function parseAudio(text: string, maxAudioBytes: number): Uint8Array {
let raw: unknown;
try {
@@ -162,10 +127,6 @@ export function createXiaomiMimoProvider(options: CreateXiaomiMimoProviderOption
const apiBaseUrl = normalizeBaseUrl(options.apiBaseUrl ?? "https://api.xiaomimimo.com/v1");
const requestTimeoutMs = positiveInteger(options.requestTimeoutMs ?? 180_000, "requestTimeoutMs");
const maxResponseBytes = positiveInteger(options.maxResponseBytes ?? 64 * 1024 * 1024, "maxResponseBytes");
- const maxVoiceSampleBase64Bytes = positiveInteger(
- options.maxVoiceSampleBase64Bytes ?? 10_000_000,
- "maxVoiceSampleBase64Bytes",
- );
const fetcher = options.fetch ?? globalThis.fetch;
const endpointCapabilities = modelNames.map((model) => ({
capability: capabilities[model],
@@ -174,19 +135,10 @@ export function createXiaomiMimoProvider(options: CreateXiaomiMimoProviderOption
handler: async (context: EndpointInvocationContext) => {
const req = request(context.need.constraints, model);
const text = scalar(req, model, "text")!;
- const messages: Array<{ role: "user" | "assistant"; content: string }> = [];
+ const messages: Array<{ role: "user" | "assistant"; content: string }> = [
+ { role: "user", content: scalar(req, model, "voiceDescription")! },
+ ];
const audio: Record<string, CanonicalValue> = { format: "wav" };
- if (model === "mimo-v2.5-tts") {
- const instruction = scalar(req, model, "instruction", false);
- if (instruction !== undefined) messages.push({ role: "user", content: instruction });
- audio.voice = scalar(req, model, "voice")!;
- } else if (model === "mimo-v2.5-tts-voicedesign") {
- messages.push({ role: "user", content: scalar(req, model, "voiceDescription")! });
- } else {
- const instruction = scalar(req, model, "instruction", false);
- if (instruction !== undefined) messages.push({ role: "user", content: instruction });
- audio.voice = await readVoiceSample(context, req, maxVoiceSampleBase64Bytes);
- }
messages.push({ role: "assistant", content: text });
const controller = new AbortController();
const timer = setTimeout(() => controller.abort(new Error("Xiaomi MiMo request timed out")), requestTimeoutMs);
diff --git a/packages/provider-xiaomi-mimo/test/provider.test.ts b/packages/provider-xiaomi-mimo/test/provider.test.ts
index 059091d6..226a278f 100644
--- a/packages/provider-xiaomi-mimo/test/provider.test.ts
+++ b/packages/provider-xiaomi-mimo/test/provider.test.ts
@@ -7,105 +7,56 @@ import { mimoTtsEndpoints, sealMimoTtsRequest } from "@hypit/mimo-tts";
import type { CanonicalValue, Need } from "@hypit/protocol";
import { createXiaomiMimoProvider } from "@hypit/provider-xiaomi-mimo";
-function need(
- endpoint: (typeof mimoTtsEndpoints)[keyof typeof mimoTtsEndpoints],
- constraints: CanonicalValue,
- id: string,
-): Need {
+function need(constraints: CanonicalValue): Need {
return {
- id: `need:${id}`,
- capability: endpoint.capability,
- returns: endpoint.returns,
+ id: "need:mimo-voicedesign",
+ capability: mimoTtsEndpoints.voiceDesign.capability,
+ returns: mimoTtsEndpoints.voiceDesign.returns,
constraints,
- result: `record:${id}`,
+ result: "record:mimo-voicedesign",
};
}
-async function invoke(request: Need, artifacts: MemoryArtifactStore, fetch: typeof globalThis.fetch) {
+test("the official Provider maps only the VoiceDesign contract", async () => {
+ const artifacts = new MemoryArtifactStore();
const provider = createXiaomiMimoProvider({
- fetch,
+ fetch: async (input, init) => {
+ assert.equal(String(input), "https://api.xiaomimimo.com/v1/chat/completions");
+ assert.equal(new Headers(init?.headers).get("api-key"), "test-key");
+ const body = JSON.parse(String(init?.body)) as Record<string, unknown>;
+ assert.equal(body.model, "mimo-v2.5-tts-voicedesign");
+ assert.deepEqual(body.audio, { format: "wav" });
+ assert.deepEqual(body.messages, [
+ { role: "user", content: "A clear, grounded female voice." },
+ { role: "assistant", content: "Keep every authored word." },
+ ]);
+ return Response.json({ choices: [{ message: { audio: { data: Buffer.from([9, 8, 7]).toString("base64") } } }] });
+ },
});
const registry = new EndpointRegistry();
await provider.install(registry);
+ const request = need(sealMimoTtsRequest("mimo-v2.5-tts-voicedesign", {
+ text: ["Keep every authored word."],
+ voiceDescription: ["A clear, grounded female voice."],
+ }) as unknown as CanonicalValue);
const resolution = registry.resolve(request);
assert.equal(resolution.status, "resolved");
assert.equal(resolution.registration.kind, "immediate");
- return await resolution.registration.handler({
- command: { kind: "fulfill-need", id: `command:${request.id}`, need: request },
+ const result = await resolution.registration.handler({
+ command: { kind: "fulfill-need", id: "command:mimo-voicedesign", need: request },
need: request,
artifacts,
credentials: { apiKey: { secret: "test-key" } },
});
-}
-
-function audioResponse(bytes: Uint8Array) {
- return Response.json({ choices: [{ message: { audio: { data: Buffer.from(bytes).toString("base64") } } }] });
-}
-
-test("the official Provider maps all three model contracts without owning them", async () => {
- const artifacts = new MemoryArtifactStore();
- const sample = await artifacts.put(new Uint8Array([1, 2, 3, 4]), "audio/wav");
- const cases = [
- {
- endpoint: mimoTtsEndpoints.preset,
- request: sealMimoTtsRequest("mimo-v2.5-tts", {
- text: ["Keep every authored word."], instruction: ["Warm and concise."], voice: ["Chloe"],
- }),
- assertBody(body: Record<string, unknown>) {
- assert.deepEqual(body.audio, { format: "wav", voice: "Chloe" });
- assert.equal((body.messages as unknown[]).length, 2);
- },
- },
- {
- endpoint: mimoTtsEndpoints.voiceDesign,
- request: sealMimoTtsRequest("mimo-v2.5-tts-voicedesign", {
- text: ["Keep every authored word."], voiceDescription: ["A clear, grounded female voice."],
- }),
- assertBody(body: Record<string, unknown>) {
- assert.deepEqual(body.audio, { format: "wav" });
- assert.equal((body.messages as unknown[]).length, 2);
- },
- },
- {
- endpoint: mimoTtsEndpoints.voiceClone,
- request: sealMimoTtsRequest("mimo-v2.5-tts-voiceclone", {
- text: ["Keep every authored word."], sample: [{ role: "audio", artifact: sample }],
- }),
- assertBody(body: Record<string, unknown>) {
- assert.match((body.audio as Record<string, string>).voice!, /^data:audio\/wav;base64,/u);
- assert.equal((body.messages as unknown[]).length, 1);
- },
- },
- ];
- for (const [index, item] of cases.entries()) {
- let calls = 0;
- const result = await invoke(
- need(item.endpoint, item.request as unknown as CanonicalValue, String(index)),
- artifacts,
- async (input, init) => {
- calls += 1;
- assert.equal(String(input), "https://api.xiaomimimo.com/v1/chat/completions");
- assert.equal(new Headers(init?.headers).get("api-key"), "test-key");
- const body = JSON.parse(String(init?.body)) as Record<string, unknown>;
- assert.equal(body.model, item.endpoint.capability.name);
- assert.equal((body.messages as Array<Record<string, unknown>>).at(-1)?.role, "assistant");
- assert.equal((body.messages as Array<Record<string, unknown>>).at(-1)?.content, "Keep every authored word.");
- assert.equal("optimize_text_preview" in (body.audio as Record<string, unknown>), false);
- item.assertBody(body);
- return audioResponse(new Uint8Array([9, 8, 7, index]));
- },
- );
- assert.equal(calls, 1);
- assert.equal(result.value.kind, "inline");
- const set = result.value.kind === "inline" ? result.value.value as Record<string, unknown> : {};
- const audios = set.audios as Array<{ mediaType: string; digest: string }>;
- assert.equal(audios[0]?.mediaType, "audio/wav");
- assert.equal(await artifacts.has(audios[0]!.digest as `sha256:${string}`), true);
- }
+ assert.equal(result.value.kind, "inline");
+ const set = result.value.kind === "inline" ? result.value.value as Record<string, unknown> : {};
+ const audios = set.audios as Array<{ mediaType: string; digest: string }>;
+ assert.equal(audios[0]?.mediaType, "audio/wav");
+ assert.equal(await artifacts.has(audios[0]!.digest as `sha256:${string}`), true);
});
test("Provider configuration owns credentials and queue policy, not model semantics", () => {
const provider = createXiaomiMimoProvider({ defaultConcurrency: 3 });
- assert.equal(provider.offers.length, 3);
- assert.ok(provider.offers.every((binding) => binding.returns.name === generationTypes.audioSet.name));
+ assert.equal(provider.offers.length, 1);
+ assert.equal(provider.offers[0]?.returns.name, generationTypes.audioSet.name);
});
diff --git a/projects/hypihub-provider-smoke/hypit.runtime.json b/projects/hypihub-provider-smoke/hypit.runtime.json
index 31f36a9a..5a2e38c0 100644
--- a/projects/hypihub-provider-smoke/hypit.runtime.json
+++ b/projects/hypihub-provider-smoke/hypit.runtime.json
@@ -15,18 +15,7 @@
"apiKey": { "store": "env", "key": "HYPIHUB_API_KEY" },
"defaultConcurrency": 8,
"pollIntervalMs": 5000,
- "requestTimeoutMs": 120000,
- "audio": false
- }
- },
- "xiaomi-mimo.smoke": {
- "use": "@hypit/provider-xiaomi-mimo",
- "pool": "xiaomi-mimo.smoke",
- "config": {
- "apiBaseUrl": "https://api.xiaomimimo.com/v1",
- "apiKey": { "store": "env", "key": "MIMO_API_KEY" },
- "defaultConcurrency": 2,
- "requestTimeoutMs": 180000
+ "requestTimeoutMs": 120000
}
}
}
diff --git a/projects/hypihub-provider-smoke/main.svml b/projects/hypihub-provider-smoke/main.svml
index 7d212ef2..d5c957d1 100644
--- a/projects/hypihub-provider-smoke/main.svml
+++ b/projects/hypihub-provider-smoke/main.svml
@@ -87,6 +87,4 @@
</gemini:Generate>
<mimo:VoiceDesign id="mimo-voice" speech={speech}>A clear, warm narrator with a lightly playful delivery.</mimo:VoiceDesign>
- <mimo:Preset id="mimo-preset" speech={speech} voice="Chloe"/>
- <mimo:VoiceClone id="mimo-clone" speech={speech} sample={reference-audio}/>
</svml>