Mistral

OverviewCopy Anchor Link

• 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.

InstallationCopy Anchor Link

bun add @pipedog/mistral

import { MistralTTSService } from "@pipedog/mistral/tts";

PrerequisitesCopy Anchor Link

• A Mistral account and an API key from Mistral.
• Pass the key as apiKey. The examples read it from MISTRAL_API_KEY.
• A voice ID for voice: the default is null.

MistralTTSServiceCopy Anchor Link

Posts to https://api.mistral.ai/v1/audio/speech.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new MistralTTSService.Settings({...}) (MistralTTSSettings). Any setting you leave out keeps the default below.

UsageCopy Anchor Link

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:

// 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" }),
});

NotesCopy Anchor Link

• Mistral returns 24 kHz audio, resampled to sampleRate when that differs.
• A failed request produces an ErrorFrame instead of audio.

Runtime notesCopy Anchor Link

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: 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.