# Mistral > Text-to-speech with MistralTTSService, Mistral's Voxtral TTS streamed over Server-Sent Events. Source: https://polvallverdu.github.io/pipedog/docs/services/tts/mistral/ ## Overview [#overview] * **`MistralTTSService`**: posts each sentence to Mistral's speech API with streaming on, converts the float32 PCM chunks to 16-bit, and resamples them from 24 kHz to the pipeline's rate. Pipecat's documentation for the same service. `packages/mistral/src/tts.ts`. Voxtral and the audio APIs. ## Installation [#installation] ```bash bun add @pipedog/mistral ``` ```ts import { MistralTTSService } from "@pipedog/mistral/tts"; ``` ## Prerequisites [#prerequisites] * A Mistral account and an API key from [Mistral](https://docs.mistral.ai/api/). * Pass the key as `apiKey`. The examples read it from `MISTRAL_API_KEY`. * A voice ID for `voice`: the default is `null`. ## MistralTTSService [#mistralttsservice] Posts to `https://api.mistral.ai/v1/audio/speech`. ### Configuration [#configuration] | Option | Type | Required | Description | |---|---|---|---| | `apiKey` | `string \| null \| undefined` | no | Mistral API key for authentication. | | `baseUrl` | `string \| null \| undefined` | no | Base URL of Mistral's API. Defaults to `"https://api.mistral.ai/v1"`. | | `settings` | `MistralTTSSettings \| null \| undefined` | no | Runtime-updatable settings. | | `name` | `string \| null \| undefined` | no | Custom name; defaults to `ClassName#count`. | | `taskManager` | `BaseTaskManager \| null \| undefined` | no | Task manager for handling tasks. | | `enableDirectMode` | `boolean \| undefined` | no | Process frames immediately instead of using internal queues. | | `metrics` | `FrameProcessorMetrics \| null \| undefined` | no | Optional metrics collector for this processor. | | `textAggregationMode` | `TextAggregationMode \| null \| undefined` | no | How to aggregate incoming text before synthesis. `TextAggregationMode.SENTENCE` (default) buffers until sentence boundaries, `TextAggregationMode.TOKEN` streams tokens directly for lower latency. | | `pushTextFrames` | `boolean \| undefined` | no | Whether to push TextFrames and LLMFullResponseEndFrames. | | `pushStopFrames` | `boolean \| undefined` | no | Whether to automatically push TTSStoppedFrames. | | `pushStartFrame` | `boolean \| undefined` | no | Whether to automatically create audio contexts and push TTSStartedFrames. When true, the base class handles `createAudioContext` and yields `TTSStartedFrame` before each synthesis call, so `runTts` implementations do not need to. | | `stopFrameTimeoutS` | `number \| undefined` | no | Idle time before pushing TTSStoppedFrame when pushStopFrames is true. | | `pushSilenceAfterStop` | `boolean \| undefined` | no | Whether to push silence audio after TTSStoppedFrame. | | `silenceTimeS` | `number \| undefined` | no | Duration of silence to push when pushSilenceAfterStop is true. | | `pauseFrameProcessing` | `boolean \| undefined` | no | Whether to hold incoming frames after a turn until its audio contexts end. Needed by services whose audio doesn't carry its request's context ID. | | `maxConsecutiveZeroAudioContexts` | `number \| undefined` | no | How many consecutive TTS contexts may complete without producing any audio before the service is reported unable to do its job. Catches a provider that accepts requests and stays silent — an unknown voice ID, say — which no error ever surfaces. Every silent context reports an error the service can carry on from, whatever the limit is; on reaching the limit the service reports a permanent error instead, stops being given work, and the pipeline worker applies its `ProcessorUnusablePolicy`. Set to 0 to report silent contexts without ever writing the service off. | | `appendTrailingSpace` | `boolean \| undefined` | no | Whether to append a trailing space to text before sending to TTS. This helps prevent some TTS services from vocalizing trailing punctuation (e.g., "dot"). Only applied in sentence aggregation mode; when streaming tokens, the incoming text's own whitespace is preserved. | | `sampleRate` | `number \| null \| undefined` | no | Output sample rate for generated audio. | | `skipTextTypes` | `string[] \| null \| undefined` | no | List of text types that should not be spoken. | | `textTransforms` | `[string, TextTransform][] \| null \| undefined` | no | A list of TextTransforms to transform text just before sending it to TTS. Each TextTransform takes the aggregated text and its type, and returns the transformed text. To register, provide a list of tuples of `[textType \| "*", transformFunction]`. | | `transportDestination` | `string \| null \| undefined` | no | Destination for generated audio frames. | | `reuseContextIdWithinTurn` | `boolean \| undefined` | no | Whether the service should reuse context IDs within the same turn. | | `audioCache` | `TTSAudioCacheStore \| null \| undefined` | no | Where to keep synthesized audio for reuse (e.g. a shared `TTSAudioCache`). Text whose audio is in the cache is served from it, with no request to the provider. Lines get there through `warmAudioCache()`, and also from live synthesis when `cacheSynthesizedAudio` allows it. Only services that yield their audio from `runTts` (HTTP and streaming-RPC services, see `supportsAudioCache`) use it, and only in sentence aggregation mode. Defaults to null (no cache). pipedog only. | | `cacheSynthesizedAudio` | `boolean \| ((text: string) => boolean) \| undefined` | no | Whether audio synthesized live is stored in `audioCache`, or a function that decides per text. Defaults to false: only warmed lines are stored, since a generated reply can repeat what the user said. pipedog only. | | `audioCacheNamespace` | `string \| undefined` | no | Extra part of the cache key, for constructor options that change the audio but are not in `settings`. pipedog only. | ### Settings [#settings] Runtime-updatable settings, passed as `settings: new MistralTTSService.Settings({...})` (`MistralTTSSettings`). Any setting you leave out keeps the default below. | Setting | Type | Default | Description | | ---------- | ---------------- | ------------------------- | ----------------------------- | | `model` | `string` | `"voxtral-mini-tts-2603"` | Speech model. | | `voice` | `string \| null` | `null` | Voice ID, sent as `voice_id`. | | `language` | `null` | `null` | Not used by this service. | ### Usage [#usage] ```ts title="tts.ts" import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames"; import { MistralTTSService } from "@pipedog/mistral/tts"; const tts = new MistralTTSService({ apiKey: process.env.MISTRAL_API_KEY ?? "", settings: new MistralTTSService.Settings({ voice: process.env.MISTRAL_VOICE_ID ?? "" }), }); ``` Change settings mid-call with an `TTSUpdateSettingsFrame`: ```ts // Queue it on the worker, or push it from a processor upstream of the service. const update = new TTSUpdateSettingsFrame({ delta: new MistralTTSService.Settings({ model: "voxtral-mini-tts-2603" }), }); ``` ### Notes [#notes] * Mistral returns 24 kHz audio, resampled to `sampleRate` when that differs. * A failed request produces an `ErrorFrame` instead of audio. ## Runtime notes [#runtime-notes] | Runtime | Works | What it needs | | ------------------ | ----- | ------------- | | Bun | ✅ yes | Nothing. | | Node.js | ✅ yes | Nothing. | | Deno | ✅ yes | Nothing. | | Cloudflare Workers | ✅ yes | Nothing. | Generated from `pipecat.runtimes` and `pipecat.compat` in `packages/mistral/package.json`: ✅ means the compat smoke test passes on that runtime. * Requests go through `fetch`, with the Server-Sent Events parsed in the service (upstream uses the `mistralai` SDK). It works on Bun, Node, Deno and Cloudflare Workers. * The request and events follow Mistral's SDK (`@mistralai/mistralai` 3.1.0, `audioSpeechComplete`) and the [streaming docs](https://docs.mistral.ai/studio/audio/text-to-speech/stream-speech): `speech.audio.delta` events with base64 `audio_data`, then `speech.audio.done`. The float32 layout of `"pcm"` audio comes from upstream Pipecat's conversion; Mistral's docs don't state it. * Tested against a local fake, not against Mistral itself.