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.

feat(examples): use MiMo VoiceDesign voices

rponeca85c5636851
diff --git a/examples/interview/hypit.runtime.json b/examples/interview/hypit.runtime.json
index 7b4d7e0f..1cda8ac8 100644
--- a/examples/interview/hypit.runtime.json
+++ b/examples/interview/hypit.runtime.json
@@ -12,13 +12,14 @@
"os": { "use": "@hypit/credential-store-os" }
},
"endpoints": {
- "kie.hypit-interview": {
- "use": "@hypit/provider-kie",
+ "hypihub.hypit-interview": {
+ "use": "@hypit/provider-hypihub",
"pool": "generation",
"config": {
- "apiKey": { "store": "os", "key": "KIE_API_KEY" },
- "defaultConcurrency": 10,
- "laneConcurrency": { "seedance-2-mini": 10 }
+ "baseUrl": "https://hypit.ai",
+ "apiKey": { "store": "os", "key": "hypihub.oauth" },
+ "defaultConcurrency": 4,
+ "requestTimeoutMs": 120000
}
},
"media.hypit-interview": {
diff --git a/examples/interview/reference.svml b/examples/interview/reference.svml
index 3b9a3b45..f0e9b297 100644
--- a/examples/interview/reference.svml
+++ b/examples/interview/reference.svml
@@ -4,6 +4,7 @@
<import from="@hypit/script@1"/>
<import as="text" from="@hypit/text@1"/>
<import as="media" from="@hypit/media@1"/>
+ <import as="mimo" from="@hypit/mimo-tts@1"/>
<import as="seedance" from="@hypit/seedance@1"/>
<import as="program" from="@hypit/program-space@1"/>
<import as="pipeline" from="@hypit/media-pipeline@1"/>
@@ -56,8 +57,14 @@
<gpt:Image id="guest-view" prompt={guest-view-prompt} aspect-ratio="9:16" resolution="2K"/>
<text:Value id="shared-view-prompt">A photograph with the texture of real iPhone footage. Generate a vertical street-interview frame, as one frame cut out of video actually shot on an iPhone: genuinely real rather than glossy, carrying the texture of video and not of a posed photograph. The background stays clearly visible, with no depth-of-field blur. Skin texture is fine and real, the light is natural, and no part of the picture is broken. Show the light-skinned young interviewer and the light-medium-skinned young woman together beside the blue Lamborghini, preserving their facial features, hair, clothing, microphone, handbag, and left-right relationship.</text:Value>
<gpt:Image id="shared-view" prompt={shared-view-prompt} aspect-ratio="9:16" resolution="2K"/>
- <media:Audio id="boy-voice" src="./assets/guy.wav"/>
- <media:Audio id="wife-voice" src="./assets/wife.wav"/>
+ <text:Value id="boy-voice-sample">Hey yo! Is this Lamborghini yours?</text:Value>
+ <mimo:VoiceDesign id="boy-voice" speech={boy-voice-sample}>
+ A young American man with a bright, casual street-interviewer delivery; energetic, lightly raspy, confident, and conversational, with quick natural pacing.
+ </mimo:VoiceDesign>
+ <text:Value id="wife-voice-sample">Mmm hmm. Give me three rules to make your first million.</text:Value>
+ <mimo:VoiceDesign id="wife-voice" speech={wife-voice-sample}>
+ A young woman with a playful, self-assured delivery; warm, expressive, slightly husky, and flirtatious, with crisp conversational English.
+ </mimo:VoiceDesign>
<media:Audio id="soundtrack" src="./assets/shared-soundtrack.m4a"/>
<media:Audio id="rule-reveal-sound" src="./assets/rule-reveal.wav"/>
<text:Value id="rule-placeholder-prompt">A clean, colorful 3D question-mark icon centered on a simple light background, with crisp edges and no readable text.</text:Value>
@@ -126,8 +133,8 @@
<seedance:Reference image={interviewer-view}/>
<seedance:Reference image={guest-view}/>
<seedance:Reference image={shared-view}/>
- <seedance:Reference audio={boy-voice}/>
- <seedance:Reference audio={wife-voice}/>
+ <seedance:Reference audio={boy-voice.audio}/>
+ <seedance:Reference audio={wife-voice.audio}/>
</seedance:ReferenceVideo>
<seedance:ReferenceVideo id="real-estate-rule-take"
@@ -137,8 +144,8 @@
<seedance:Reference image={interviewer-view}/>
<seedance:Reference image={guest-view}/>
<seedance:Reference image={shared-view}/>
- <seedance:Reference audio={boy-voice}/>
- <seedance:Reference audio={wife-voice}/>
+ <seedance:Reference audio={boy-voice.audio}/>
+ <seedance:Reference audio={wife-voice.audio}/>
</seedance:ReferenceVideo>
<seedance:ReferenceVideo id="bitcoin-rule-take"
@@ -148,8 +155,8 @@
<seedance:Reference image={interviewer-view}/>
<seedance:Reference image={guest-view}/>
<seedance:Reference image={shared-view}/>
- <seedance:Reference audio={boy-voice}/>
- <seedance:Reference audio={wife-voice}/>
+ <seedance:Reference audio={boy-voice.audio}/>
+ <seedance:Reference audio={wife-voice.audio}/>
</seedance:ReferenceVideo>
<space:Canvas id="vertical" width="720" height="1280"/>
diff --git a/examples/podcast/hypit.runtime.json b/examples/podcast/hypit.runtime.json
index 39386913..ac0724a0 100644
--- a/examples/podcast/hypit.runtime.json
+++ b/examples/podcast/hypit.runtime.json
@@ -17,7 +17,8 @@
"use": "@hypit/provider-hypihub",
"pool": "generation",
"config": {
- "apiKey": { "store": "env", "key": "HYPIHUB_API_KEY" },
+ "baseUrl": "https://hypit.ai",
+ "apiKey": { "store": "os", "key": "hypihub.oauth" },
"defaultConcurrency": 4,
"requestTimeoutMs": 120000
}
diff --git a/examples/podcast/reference.svml b/examples/podcast/reference.svml
index 18fb44ef..0994e6bc 100644
--- a/examples/podcast/reference.svml
+++ b/examples/podcast/reference.svml
@@ -3,6 +3,7 @@
<svml>
<import from="@hypit/script@1"/>
<import as="asset" from="@hypit/media@1"/>
+ <import as="mimo" from="@hypit/mimo-tts@1"/>
<import as="text" from="@hypit/text@1"/>
<import as="gpt" from="@hypit/gpt-image@1"/>
<import as="seedance" from="@hypit/seedance@1"/>
@@ -52,8 +53,14 @@
<text:Value id="creatine-prompt">A photograph with the texture of real iPhone footage. Generate a vertical medium close-up, as one frame cut out of video actually shot on an iPhone: genuinely real rather than glossy, carrying the texture of video and not of a posed photograph. The background stays clearly visible, with no depth-of-field blur. Skin texture is fine and real, the light is natural, and no part of the picture is broken. single creatine supplement tub with a squat cylindrical body, wide lid, and bold product label centered in the frame, with its shape, cap, label placement, and hand scale clearly readable. Use a short neutral product backdrop and no extra objects.</text:Value>
<gpt:Image id="creatine" prompt={creatine-prompt} aspect-ratio="9:16" resolution="2K"/>
- <asset:Audio id="guy-voice" src="./assets/dude.mp3"/>
- <asset:Audio id="girl-voice" src="./assets/girl.wav"/>
+ <text:Value id="guy-voice-sample">OK Sarah, so what is the one single thing that you literally can't live without?</text:Value>
+ <mimo:VoiceDesign id="guy-voice" speech={guy-voice-sample}>
+ A young East Asian man with a curious, friendly podcast-host delivery; clear, relaxed, lightly nasal, and conversational, with an easy medium pace.
+ </mimo:VoiceDesign>
+ <text:Value id="girl-voice-sample">Creatine. Five grams a day, every day.</text:Value>
+ <mimo:VoiceDesign id="girl-voice" speech={girl-voice-sample}>
+ A young East Asian woman with a confident, lively podcast delivery; clear, bright, athletic, and matter-of-fact, with expressive emphasis and natural pacing.
+ </mimo:VoiceDesign>
<asset:Audio id="soundtrack" src="./assets/shared-soundtrack.m4a"/>
<text:Value id="split-prompt">
@@ -157,7 +164,7 @@
prompt={opening-take-prompt} duration="4"
resolution="720p" aspect-ratio="9:16" generate-audio="true">
<seedance:Reference image={split.image}/>
- <seedance:Reference audio={guy-voice}/>
+ <seedance:Reference audio={guy-voice.audio}/>
</seedance:ReferenceVideo>
<seedance:ReferenceVideo id="daily-creatine-take" model="mini"
@@ -165,8 +172,8 @@
resolution="720p" aspect-ratio="9:16" generate-audio="true">
<seedance:Reference image={girl-hold.image}/>
<seedance:Reference image={guy}/>
- <seedance:Reference audio={girl-voice}/>
- <seedance:Reference audio={guy-voice}/>
+ <seedance:Reference audio={girl-voice.audio}/>
+ <seedance:Reference audio={guy-voice.audio}/>
</seedance:ReferenceVideo>
<seedance:ReferenceVideo id="arms-are-asking-take" model="mini"
@@ -174,8 +181,8 @@
resolution="720p" aspect-ratio="9:16" generate-audio="true">
<seedance:Reference image={girl-hold.image}/>
<seedance:Reference image={guy-hold.image}/>
- <seedance:Reference audio={girl-voice}/>
- <seedance:Reference audio={guy-voice}/>
+ <seedance:Reference audio={girl-voice.audio}/>
+ <seedance:Reference audio={guy-voice.audio}/>
</seedance:ReferenceVideo>
<space:Canvas id="vertical" width="720" height="1280"/>
diff --git a/examples/ranking-football/hypit.runtime.json b/examples/ranking-football/hypit.runtime.json
index a284ccd1..17b03ee2 100644
--- a/examples/ranking-football/hypit.runtime.json
+++ b/examples/ranking-football/hypit.runtime.json
@@ -12,12 +12,14 @@
"os": { "use": "@hypit/credential-store-os" }
},
"endpoints": {
- "kie.football-ranking": {
- "use": "@hypit/provider-kie",
+ "hypihub.football-ranking": {
+ "use": "@hypit/provider-hypihub",
"pool": "generation",
"config": {
- "apiKey": { "store": "os", "key": "KIE_API_KEY" },
- "defaultConcurrency": 10
+ "baseUrl": "https://hypit.ai",
+ "apiKey": { "store": "os", "key": "hypihub.oauth" },
+ "defaultConcurrency": 4,
+ "requestTimeoutMs": 120000
}
},
"media.football-ranking": {
diff --git a/examples/ranking-football/reference.svml b/examples/ranking-football/reference.svml
index 719262f4..b096fc4f 100644
--- a/examples/ranking-football/reference.svml
+++ b/examples/ranking-football/reference.svml
@@ -4,6 +4,7 @@
<import from="@hypit/script@1"/>
<import as="text" from="@hypit/text@1"/>
<import as="asset" from="@hypit/media@1"/>
+ <import as="mimo" from="@hypit/mimo-tts@1"/>
<import as="gpt" from="@hypit/gpt-image@1"/>
<import as="estimate" from="@hypit/estimate@1"/>
<import as="seedance" from="@hypit/seedance@1"/>
@@ -38,7 +39,10 @@
<text:Value id="presenter-prompt">A photograph with the texture of real iPhone footage. Generate a vertical medium close-up, as one frame cut out of video actually shot on an iPhone: genuinely real rather than glossy, carrying the texture of video and not of a posed photograph. The background stays clearly visible, with no depth-of-field blur. Skin texture is fine and real, the light is natural, and no part of the picture is broken. A pale young woman with a narrow oval face, large gray eyes, straight brows, long jet-black hair with blunt bangs, and a slim shoulder line wears a black spiked cap, black choker, layered silver necklaces, and a black graphic top while holding a furry microphone. Keep her face, hair, shoulders, and microphone visible.</text:Value>
<gpt:Image id="presenter" prompt={presenter-prompt} aspect-ratio="9:16" resolution="2K"/>
- <asset:Audio id="presenter-voice" src="./assets/goth.wav"/>
+ <text:Value id="presenter-voice-sample">Welcome back. Today we're ranking the most ridiculous football takes.</text:Value>
+ <mimo:VoiceDesign id="presenter-voice" speech={presenter-voice-sample}>
+ A young woman with a smoky, low-register alt voice and dry sarcastic presenter delivery; cool, composed, slightly deadpan, with sharp comedic timing and confident emphasis.
+ </mimo:VoiceDesign>
<asset:Audio id="soundtrack" src="./assets/shared-soundtrack.m4a"/>
<asset:Audio id="ranking-appear-sfx" src="./assets/ranking-appear.wav"/>
<asset:Audio id="ranking-move-sfx" src="./assets/ranking-move.wav"/>
@@ -139,13 +143,13 @@
prompt={ronaldo-prompt} duration="10"
resolution="720p" aspect-ratio="9:16" generate-audio="true">
<seedance:Reference image={presenter}/>
- <seedance:Reference audio={presenter-voice}/>
+ <seedance:Reference audio={presenter-voice.audio}/>
</seedance:ReferenceVideo>
<seedance:ReferenceVideo id="messi-take" model="mini"
prompt={messi-prompt} duration="10"
resolution="720p" aspect-ratio="9:16" generate-audio="true">
<seedance:Reference image={presenter}/>
- <seedance:Reference audio={presenter-voice}/>
+ <seedance:Reference audio={presenter-voice.audio}/>
</seedance:ReferenceVideo>
<space:Canvas id="vertical" width="720" height="1280"/>