Your lightweight open-source personal agent.
Python agent-frameworkai-agentai-agentschatbotchatopsdiscord-botllm-agentsllmslocal-llmmcpmodel-context-protocolmulti-agentopenai-compatibleopenclawpersonal-ai-assistantpythonself-hostedtelegram-bot-ai-assistantwebuiworkflow-automation
feat(transcription): add Xiaomi MiMo ASR provider (mimo-v2.5-asr)
NanoBotc20ecc52d7a1
diff --git a/docs/configuration.md b/docs/configuration.mdindex 06c83353b..1ae86d5fc 100644--- a/docs/configuration.md+++ b/docs/configuration.md@@ -119,7 +119,7 @@ ANTHROPIC_API_KEY="$(bw get password api/anthropic)" nanobot agent## Providers> [!TIP]-> - **Voice transcription**: Voice messages and WebUI/desktop microphone input use the shared top-level `transcription` settings. By default Groq Whisper is used; set `transcription.provider` to `"openai"` for OpenAI Whisper or `"openrouter"` for OpenRouter speech-to-text models. API keys still live in the matching `providers.<provider>` config.+> - **Voice transcription**: Voice messages and WebUI/desktop microphone input use the shared top-level `transcription` settings. By default Groq Whisper is used; set `transcription.provider` to `"openai"` for OpenAI Whisper, `"openrouter"` for OpenRouter speech-to-text models, or `"xiaomi_mimo"` for Xiaomi MiMo ASR. API keys still live in the matching `providers.<provider>` config.> - **MiniMax Coding Plan**: Exclusive discount links for the nanobot community: [Overseas](https://platform.minimax.io/subscribe/coding-plan?code=9txpdXw04g&source=link) · [Mainland China](https://platform.minimaxi.com/subscribe/token-plan?code=GILTJpMTqZ&source=link)> - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config.> - **MiniMax thinking mode**: Use `providers.minimaxAnthropic` when you want `reasoningEffort` / thinking mode. MiniMax exposes that capability through its Anthropic-compatible endpoint, so nanobot keeps it as a separate provider instead of guessing MiniMax-specific thinking parameters on the generic OpenAI-compatible `minimax` endpoint. It uses the same `MINIMAX_API_KEY`. Default Anthropic-compatible base URL: `https://api.minimax.io/anthropic`; for mainland China use `https://api.minimaxi.com/anthropic`.@@ -1122,8 +1122,8 @@ Configure transcription under the top-level `transcription` section:| Setting | Default | Description ||---------|---------|-------------|| `enabled` | `true` | Enables audio transcription for both chat-channel voice messages and WebUI/desktop microphone input. |-| `provider` | `"groq"` | Transcription backend: `"groq"`, `"openai"`, or `"openrouter"`. |-| `model` | provider default | Optional transcription model override. Defaults to `whisper-large-v3` for Groq, `whisper-1` for OpenAI, and `openai/whisper-1` for OpenRouter. OpenRouter accepts only speech-to-text models on its transcription endpoint, such as `nvidia/parakeet-tdt-0.6b-v3`, `openai/whisper-1`, or `openai/gpt-4o-transcribe`; chat LLMs are rejected there. |+| `provider` | `"groq"` | Transcription backend: `"groq"`, `"openai"`, `"openrouter"`, or `"xiaomi_mimo"`. |+| `model` | provider default | Optional transcription model override. Defaults to `whisper-large-v3` for Groq, `whisper-1` for OpenAI, `openai/whisper-1` for OpenRouter, and `mimo-v2.5-asr` for Xiaomi MiMo ASR. OpenRouter accepts only speech-to-text models on its transcription endpoint, such as `nvidia/parakeet-tdt-0.6b-v3`, `openai/whisper-1`, or `openai/gpt-4o-transcribe`; chat LLMs are rejected there. || `language` | `null` | Optional ISO-639 language hint, e.g. `"en"`, `"zh"`, `"ko"`, or `"ja"`. || `maxDurationSec` | `120` | Maximum WebUI/desktop recording duration. || `maxUploadMb` | `25` | Maximum WebUI/desktop audio upload size. |diff --git a/nanobot/audio/transcription.py b/nanobot/audio/transcription.pyindex cc7cf286d..7e97517fa 100644--- a/nanobot/audio/transcription.py+++ b/nanobot/audio/transcription.py@@ -18,13 +18,18 @@ from loguru import loggerfrom nanobot.config.paths import get_media_dirfrom nanobot.utils.media_decode import FileSizeExceeded, save_base64_data_url-TranscriptionProviderName = Literal["groq", "openai", "openrouter"]+TranscriptionProviderName = Literal["groq", "openai", "openrouter", "xiaomi_mimo"]_DEFAULT_PROVIDER: TranscriptionProviderName = "groq"_DEFAULT_MODELS: dict[TranscriptionProviderName, str] = {"groq": "whisper-large-v3","openai": "whisper-1","openrouter": "openai/whisper-1",+ "xiaomi_mimo": "mimo-v2.5-asr",+}+_PROVIDER_ALIASES: dict[str, TranscriptionProviderName] = {+ "mimo": "xiaomi_mimo",+ "xiaomi": "xiaomi_mimo",}_MAX_AUDIO_BYTES_FALLBACK = 25 * 1024 * 1024_AUDIO_MIME_ALLOWED: frozenset[str] = frozenset({@@ -69,6 +74,8 @@ class TranscriptionIngressError(Exception):def _as_provider(value: Any) -> TranscriptionProviderName | None:if isinstance(value, str):name = value.strip().lower()+ if name in _PROVIDER_ALIASES:+ return _PROVIDER_ALIASES[name]if name in _DEFAULT_MODELS:return name # type: ignore[return-value]return None@@ -181,6 +188,15 @@ async def transcribe_audio_file(language=config.language,model=config.model,)+ elif config.provider == "xiaomi_mimo":+ from nanobot.providers.transcription import XiaomiMiMoTranscriptionProvider++ provider = XiaomiMiMoTranscriptionProvider(+ api_key=config.api_key,+ api_base=config.api_base or None,+ language=config.language,+ model=config.model,+ )else:from nanobot.providers.transcription import GroqTranscriptionProviderdiff --git a/nanobot/config/schema.py b/nanobot/config/schema.pyindex ba72d3729..e597052d6 100644--- a/nanobot/config/schema.py+++ b/nanobot/config/schema.py@@ -47,7 +47,7 @@ class TranscriptionConfig(Base):"""Cross-channel audio transcription configuration."""enabled: bool = True- provider: Literal["groq", "openai", "openrouter"] | None = None+ provider: Literal["groq", "openai", "openrouter", "xiaomi_mimo"] | None = Nonemodel: str | None = Nonelanguage: str | None = Field(default=None, pattern=r"^[a-z]{2,3}$")max_duration_sec: int = Field(default=120, ge=1, le=600)diff --git a/nanobot/providers/transcription.py b/nanobot/providers/transcription.pyindex 7d4a0c013..997228bd0 100644--- a/nanobot/providers/transcription.py+++ b/nanobot/providers/transcription.py@@ -1,8 +1,9 @@"""Provider-specific voice transcription adapters.This module only knows how to call external transcription APIs such as Groq,-OpenAI Whisper, and OpenRouter. Product-level config fallback, WebUI upload-validation, and channel integration live in ``nanobot.audio.transcription``.+OpenAI Whisper, OpenRouter, and Xiaomi MiMo ASR. Product-level config fallback,+WebUI upload validation, and channel integration live in+``nanobot.audio.transcription``."""import asyncio@@ -16,6 +17,7 @@ from typing import Anyimport httpxfrom loguru import logger+_CHAT_COMPLETIONS_PATH = "chat/completions"_TRANSCRIPTIONS_PATH = "audio/transcriptions"_AUDIO_MIME_OVERRIDES = {".m4a": "audio/mp4",@@ -51,6 +53,16 @@ def _resolve_transcription_url(api_base: str | None, default_url: str) -> str:return f"{base}/{_TRANSCRIPTIONS_PATH}"+def _resolve_chat_completions_url(api_base: str | None, default_url: str) -> str:+ """Resolve a chat-completions endpoint for ASR providers using chat payloads."""+ if not api_base:+ return default_url+ base = api_base.rstrip("/")+ if base.endswith(_CHAT_COMPLETIONS_PATH):+ return base+ return f"{base}/{_CHAT_COMPLETIONS_PATH}"++def _audio_mime_type(path: Path) -> str:return (_AUDIO_MIME_OVERRIDES.get(path.suffix.lower())@@ -116,7 +128,7 @@ async def _post_transcription_with_retry(files["language"] = (None, language)return {"url": url, "headers": headers, "files": files, "timeout": 60.0}- return await _post_with_retry(build_request, provider_label)+ return await _post_with_retry(build_request, provider_label, _text_from_transcription_payload)async def _post_json_transcription_with_retry(@@ -151,12 +163,61 @@ async def _post_json_transcription_with_retry(body["language"] = languagereturn {"url": url, "headers": headers, "json": body, "timeout": 60.0}- return await _post_with_retry(build_request, provider_label)+ return await _post_with_retry(build_request, provider_label, _text_from_transcription_payload)+++async def _post_xiaomi_mimo_asr_with_retry(+ url: str,+ *,+ api_key: str | None,+ path: Path,+ model: str,+ provider_label: str,+ language: str | None = None,+) -> str:+ """POST audio to Xiaomi MiMo ASR's chat-completions transcription API."""+ try:+ data = path.read_bytes()+ except OSError as e:+ logger.exception("{} transcription error: cannot read audio file: {}", provider_label, e)+ return ""++ body: dict[str, Any] = {+ "model": model,+ "messages": [+ {+ "role": "user",+ "content": [+ {+ "type": "input_audio",+ "input_audio": {+ "data": (+ f"data:{_audio_mime_type(path)};base64,"+ f"{base64.b64encode(data).decode('ascii')}"+ ),+ },+ }+ ],+ }+ ],+ }+ if language:+ body["asr_options"] = {"language": language}+ headers = {+ "Authorization": f"Bearer {api_key}",+ "Content-Type": "application/json",+ }++ def build_request() -> dict[str, Any]:+ return {"url": url, "headers": headers, "json": body, "timeout": 60.0}++ return await _post_with_retry(build_request, provider_label, _text_from_chat_payload)async def _post_with_retry(build_request: Callable[[], dict[str, Any]],provider_label: str,+ extract_text: Callable[[dict[str, Any]], str],) -> str:async with httpx.AsyncClient() as client:for attempt in range(_MAX_RETRIES + 1):@@ -227,10 +288,23 @@ async def _post_with_retry(type(payload).__name__,)return ""- return payload.get("text", "")+ return extract_text(payload)return ""+def _text_from_transcription_payload(payload: dict[str, Any]) -> str:+ text = payload.get("text")+ return text if isinstance(text, str) else ""+++def _text_from_chat_payload(payload: dict[str, Any]) -> str:+ try:+ text = payload["choices"][0]["message"]["content"]+ except (KeyError, IndexError, TypeError):+ return ""+ return text if isinstance(text, str) else ""++class OpenAITranscriptionProvider:"""Voice transcription provider using OpenAI's Whisper API."""@@ -357,3 +431,42 @@ class OpenRouterTranscriptionProvider:provider_label="OpenRouter",language=self.language,)+++class XiaomiMiMoTranscriptionProvider:+ """Voice transcription provider using Xiaomi MiMo ASR."""++ def __init__(+ self,+ api_key: str | None = None,+ api_base: str | None = None,+ language: str | None = None,+ model: str | None = None,+ ):+ self.api_key = api_key or os.environ.get("MIMO_API_KEY")+ self.api_url = _resolve_chat_completions_url(+ api_base or os.environ.get("MIMO_API_BASE"),+ "https://api.xiaomimimo.com/v1/chat/completions",+ )+ self.language = language or None+ self.model = model or "mimo-v2.5-asr"+ logger.debug("Xiaomi MiMo transcription endpoint: {}", self.api_url)++ async def transcribe(self, file_path: str | Path) -> str:+ if not self.api_key:+ logger.warning("Xiaomi MiMo API key not configured for transcription")+ return ""++ path = Path(file_path)+ if not path.exists():+ logger.error("Audio file not found: {}", file_path)+ return ""++ return await _post_xiaomi_mimo_asr_with_retry(+ self.api_url,+ api_key=self.api_key,+ path=path,+ model=self.model,+ provider_label="Xiaomi MiMo",+ language=self.language,+ )diff --git a/nanobot/webui/settings_api.py b/nanobot/webui/settings_api.pyindex cc6d76f82..71c7e08bf 100644--- a/nanobot/webui/settings_api.py+++ b/nanobot/webui/settings_api.py@@ -91,7 +91,7 @@ _IMAGE_GENERATION_ASPECT_RATIOS = {"2:3","21:9",}-_TRANSCRIPTION_PROVIDERS = ("groq", "openai", "openrouter")+_TRANSCRIPTION_PROVIDERS = ("groq", "openai", "openrouter", "xiaomi_mimo")_CONTEXT_WINDOW_TOKEN_OPTIONS = {65_536, 262_144}_MODEL_CONFIGURATION_SLUG_RE = re.compile(r"[^a-z0-9_-]+")_ENV_REF_RE = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")diff --git a/tests/providers/test_transcription.py b/tests/providers/test_transcription.pyindex 3fa3714da..574d5a44b 100644--- a/tests/providers/test_transcription.py+++ b/tests/providers/test_transcription.py@@ -19,7 +19,9 @@ from nanobot.providers.transcription import (GroqTranscriptionProvider,OpenAITranscriptionProvider,OpenRouterTranscriptionProvider,+ XiaomiMiMoTranscriptionProvider,_audio_format,+ _resolve_chat_completions_url,_resolve_transcription_url,)@@ -95,6 +97,37 @@ def test_resolver_supports_openrouter_transcription_provider() -> None:assert resolved.api_base == "https://openrouter.ai/api/v1"+def test_resolver_supports_xiaomi_mimo_transcription_provider() -> None:+ config = Config()+ config.transcription.provider = "xiaomi_mimo"+ config.transcription.model = "mimo-v2.5-asr"+ config.transcription.language = "zh"+ config.providers.xiaomi_mimo.api_key = "mimo-test"+ config.providers.xiaomi_mimo.api_base = "https://api.xiaomimimo.com/v1"++ resolved = resolve_transcription_config(config)++ assert resolved.provider == "xiaomi_mimo"+ assert resolved.model == "mimo-v2.5-asr"+ assert resolved.language == "zh"+ assert resolved.api_key == "mimo-test"+ assert resolved.api_base == "https://api.xiaomimimo.com/v1"+++def test_resolver_accepts_legacy_xiaomi_transcription_alias() -> None:+ config = Config()+ config.channels.transcription_provider = "xiaomi"+ config.channels.transcription_language = "zh"+ config.providers.xiaomi_mimo.api_key = "mimo-test"++ resolved = resolve_transcription_config(config)++ assert resolved.provider == "xiaomi_mimo"+ assert resolved.model == "mimo-v2.5-asr"+ assert resolved.language == "zh"+ assert resolved.api_key == "mimo-test"++@pytest.mark.asyncioasync def test_transcribe_audio_file_routes_openrouter_provider(audio_file: Path) -> None:captured: dict[str, object] = {}@@ -131,6 +164,42 @@ async def test_transcribe_audio_file_routes_openrouter_provider(audio_file: Path}+async def test_transcribe_audio_file_routes_xiaomi_mimo_provider(audio_file: Path) -> None:+ captured: dict[str, object] = {}++ class StubXiaomiMiMo:+ def __init__(self, **kwargs):+ captured.update(kwargs)++ async def transcribe(self, file_path: str | Path) -> str:+ captured["file_path"] = Path(file_path)+ return "mimo ok"++ config = EffectiveTranscriptionConfig(+ enabled=True,+ provider="xiaomi_mimo",+ model="mimo-v2.5-asr",+ language="zh",+ api_key="mimo-test",+ api_base="https://api.xiaomimimo.com/v1",+ max_duration_sec=120,+ max_upload_mb=25,+ )++ with patch("nanobot.providers.transcription.XiaomiMiMoTranscriptionProvider", StubXiaomiMiMo):+ result = await transcribe_audio_file(audio_file, config)++ assert result == "mimo ok"+ assert captured == {+ "api_key": "mimo-test",+ "api_base": "https://api.xiaomimimo.com/v1",+ "language": "zh",+ "model": "mimo-v2.5-asr",+ "file_path": audio_file,+ }++def test_resolved_transcription_repr_hides_api_key() -> None:config = Config()config.providers.groq.api_key = "gsk-secret"@@ -496,6 +565,69 @@ async def test_openrouter_shares_retry_contract(audio_file: Path) -> None:assert post.await_count == 2+def test_resolve_chat_completions_url_appends_path_to_base() -> None:+ default = "https://api.xiaomimimo.com/v1/chat/completions"+ assert _resolve_chat_completions_url(None, default) == default+ assert (+ _resolve_chat_completions_url("https://api.xiaomimimo.com/v1", default)+ == "https://api.xiaomimimo.com/v1/chat/completions"+ )+ assert _resolve_chat_completions_url(default, "https://x/chat/completions") == default+++def test_xiaomi_mimo_defaults_and_base_normalization() -> None:+ provider = XiaomiMiMoTranscriptionProvider(api_key="k")+ assert provider.api_url == "https://api.xiaomimimo.com/v1/chat/completions"+ assert provider.model == "mimo-v2.5-asr"++ custom = XiaomiMiMoTranscriptionProvider(+ api_key="k",+ api_base="https://token-plan-sgp.xiaomimimo.com/v1",+ model="custom-asr",+ )+ assert custom.api_url == "https://token-plan-sgp.xiaomimimo.com/v1/chat/completions"+ assert custom.model == "custom-asr"+++async def test_xiaomi_mimo_sends_chat_completion_audio_payload(audio_file: Path) -> None:+ provider = XiaomiMiMoTranscriptionProvider(api_key="k", language="zh")+ post = AsyncMock(+ return_value=_response(+ 200,+ {"choices": [{"message": {"content": "你好"}}]},+ )+ )++ with patch("httpx.AsyncClient.post", post), patch("asyncio.sleep", AsyncMock()):+ assert await provider.transcribe(audio_file) == "你好"++ call = post.await_args_list[0].kwargs+ assert "files" not in call+ body = call["json"]+ assert body["model"] == "mimo-v2.5-asr"+ assert body["asr_options"] == {"language": "zh"}+ audio = body["messages"][0]["content"][0]["input_audio"]["data"]+ assert audio.startswith("data:audio/ogg;base64,")+ assert base64.b64decode(audio.split(",", 1)[1]) == audio_file.read_bytes()+++async def test_xiaomi_mimo_shares_retry_contract(audio_file: Path) -> None:+ provider = XiaomiMiMoTranscriptionProvider(api_key="k")+ post = AsyncMock(+ side_effect=[+ _response(503),+ _response(200, {"choices": [{"message": {"content": "ok"}}]}),+ ]+ )++ with patch("httpx.AsyncClient.post", post), patch("asyncio.sleep", AsyncMock()):+ assert await provider.transcribe(audio_file) == "ok"++ assert post.await_count == 2++@pytest.mark.parametrize("status", [408, 429, 500, 502, 503, 504])@pytest.mark.asyncioasync def test_retries_on_every_advertised_transient_status(diff --git a/tests/webui/test_settings_api.py b/tests/webui/test_settings_api.pyindex 80fcf29b1..754a74449 100644--- a/tests/webui/test_settings_api.py+++ b/tests/webui/test_settings_api.py@@ -282,6 +282,23 @@ def test_settings_payload_exposes_openrouter_transcription_provider(assert providers["openrouter"]["configured"] is True+def test_settings_payload_exposes_xiaomi_mimo_transcription_provider(+ tmp_path,+ monkeypatch: pytest.MonkeyPatch,+) -> None:+ config_path = tmp_path / "config.json"+ config = Config()+ config.providers.xiaomi_mimo.api_key = "mimo-test"+ save_config(config, config_path)+ monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)++ payload = settings_payload()++ providers = {provider["name"]: provider for provider in payload["transcription"]["providers"]}+ assert providers["xiaomi_mimo"]["label"] == "Xiaomi MIMO"+ assert providers["xiaomi_mimo"]["configured"] is True++def test_update_transcription_settings_writes_top_level_only(tmp_path,monkeypatch: pytest.MonkeyPatch,@@ -342,6 +359,32 @@ def test_update_transcription_settings_accepts_openrouter(assert payload["transcription"]["provider_configured"] is True+def test_update_transcription_settings_accepts_xiaomi_mimo(+ tmp_path,+ monkeypatch: pytest.MonkeyPatch,+) -> None:+ config_path = tmp_path / "config.json"+ config = Config()+ config.providers.xiaomi_mimo.api_key = "mimo-test"+ save_config(config, config_path)+ monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)++ payload = update_transcription_settings(+ {+ "provider": ["xiaomi_mimo"],+ "model": ["mimo-v2.5-asr"],+ "language": ["zh"],+ }+ )++ saved = load_config(config_path)+ assert saved.transcription.provider == "xiaomi_mimo"+ assert saved.transcription.model == "mimo-v2.5-asr"+ assert saved.transcription.language == "zh"+ assert payload["transcription"]["provider"] == "xiaomi_mimo"+ assert payload["transcription"]["provider_configured"] is True++def test_update_transcription_settings_validates_language(tmp_path,monkeypatch: pytest.MonkeyPatch,