From c1d1f72f439063b285a5d609f6eff84935099f18 Mon Sep 17 00:00:00 2001 From: Chesars Date: Wed, 4 Mar 2026 16:26:53 -0300 Subject: [PATCH] docs: add Mistral Voxtral audio transcription documentation Add Mistral to the supported providers list in audio_transcription.md and add Audio Transcription section to the Mistral provider page with SDK usage, optional params, diarize support, and proxy configuration. --- docs/my-website/docs/audio_transcription.md | 3 +- docs/my-website/docs/providers/mistral.md | 73 +++++++++++++++++++++ 2 files changed, 75 insertions(+), 1 deletion(-) diff --git a/docs/my-website/docs/audio_transcription.md b/docs/my-website/docs/audio_transcription.md index 5853b5c1872..7452a7007b7 100644 --- a/docs/my-website/docs/audio_transcription.md +++ b/docs/my-website/docs/audio_transcription.md @@ -13,7 +13,7 @@ import TabItem from '@theme/TabItem'; | Fallbacks | ✅ | Works between supported models | | Loadbalancing | ✅ | Works between supported models | | Guardrails | ✅ | Applies to output transcribed text (non-streaming only) | -| Supported Providers | `openai`, `azure`, `vertex_ai`, `gemini`, `deepgram`, `groq`, `fireworks_ai`, `ovhcloud` | | +| Supported Providers | `openai`, `azure`, `vertex_ai`, `gemini`, `deepgram`, `groq`, `fireworks_ai`, `ovhcloud`, `mistral` | | ## Quick Start @@ -126,6 +126,7 @@ transcript = client.audio.transcriptions.create( - [Fireworks AI](./providers/fireworks_ai.md#audio-transcription) - [Groq](./providers/groq.md#speech-to-text---whisper) - [Deepgram](./providers/deepgram.md) +- [Mistral (Voxtral)](./providers/mistral.md#audio-transcription) - [OVHcloud AI Endpoints](./providers/ovhcloud.md) --- diff --git a/docs/my-website/docs/providers/mistral.md b/docs/my-website/docs/providers/mistral.md index e0fccba7866..8355cd2464c 100644 --- a/docs/my-website/docs/providers/mistral.md +++ b/docs/my-website/docs/providers/mistral.md @@ -311,6 +311,79 @@ print(response) - **Model Compatibility**: Reasoning parameters only work with magistral models - **Backward Compatibility**: Non-magistral models will ignore reasoning parameters and work normally +## Audio Transcription + +Use Mistral's Voxtral models for audio transcription via `litellm.transcription()`. + +### SDK Usage + +```python +from litellm import transcription +import os + +os.environ["MISTRAL_API_KEY"] = "" + +audio_file = open("path/to/audio.wav", "rb") + +response = transcription( + model="mistral/voxtral-mini-latest", + file=audio_file, +) + +print(response.text) +``` + +### With Optional Parameters + +```python +response = transcription( + model="mistral/voxtral-mini-latest", + file=audio_file, + language="en", + temperature=0.0, + response_format="json", +) +``` + +### Mistral-Specific Parameters + +Mistral supports additional parameters beyond the OpenAI-compatible ones: + +| Parameter | Type | Description | +|-----------|------|-------------| +| `diarize` | `bool` | Enable speaker diarization | + +```python +response = transcription( + model="mistral/voxtral-mini-latest", + file=audio_file, + diarize=True, +) +``` + +### Usage with LiteLLM Proxy + +```yaml +model_list: + - model_name: voxtral + litellm_params: + model: mistral/voxtral-mini-latest + api_key: os.environ/MISTRAL_API_KEY + model_info: + mode: audio_transcription +``` + +```bash +litellm --config /path/to/config.yaml +``` + +```bash +curl --location 'http://0.0.0.0:4000/v1/audio/transcriptions' \ +--header 'Authorization: Bearer sk-1234' \ +--form 'file=@"audio.wav"' \ +--form 'model="voxtral"' +``` + ## Sample Usage - Embedding ```python from litellm import embedding