Voxtral 3

Mistral's speech family: transcription from $0.0035/min, a multilingual TTS model, and a LiveKit-based voice agent SDK.

Mistral AI · Generative media (image, video, audio, music, voice/avatar generation) · model

Published in Feed

This entry is marked for review. Check the original sources before relying on its details.

Overview

Mistral released Voxtral 3 on October 20, 2026 as a family of speech-to-text and text-to-speech models plus a voice agent SDK. It includes Voxtral Small Transcribe 3 ($0.004/min, 50+ languages, diarization, context biasing), Voxtral Mini Transcribe 3 (4B parameters, $0.0035/min, batch), Voxtral Mini Transcribe Realtime 3 ($0.008/min, sub-500ms latency), and Voxtral Mini TTS 3 ($13 per 1M characters, 35+ languages and 50+ dialects, voice cloning from 30+ minutes of audio). The SDK is built on LiveKit and chains speech-in, reasoning, tool calls, and speech-out in one streaming pipeline over SIP and WebRTC. The 2025-era Voxtral Small 24B STT model is catalogued separately.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Voxtral Small Transcribe 3: 50+ languages, diarization, context biasing, $0.004/min
  • Voxtral Mini Transcribe 3: 4B parameters, batch transcription, $0.0035/min
  • Voxtral Mini Transcribe Realtime 3: sub-500ms latency, $0.008/min
  • Voxtral Mini TTS 3: 35+ languages and 50+ dialects, voice cloning from 30+ minutes of audio, $13 per 1M characters
  • LiveKit-based voice agent SDK with SIP (phone) and WebRTC (browser/app) connectivity; each stage swappable
  • Available via Mistral API with EU, US, and global endpoints, or self-deployed

Use cases

  • Real-time phone and web voice agents
  • Meeting and call transcription with speaker diarization
  • Multilingual voice-over with cloned voices

Pricing

API per-use: $0.0035/min (Mini Transcribe 3), $0.004/min (Small Transcribe 3), $0.008/min (Realtime), $13 per 1M characters (TTS); voice agent SDK $0.04/min with Mistral Small 4 or $0.08/min with a larger model. Licenses not stated on the launch page.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
20 Oct 2026
Record updated
23 Oct 2026
Record last checked
23 Oct 2026

Explore the Feed

Other entries filed under generative media (image, video, audio, music, voice/avatar generation); inclusion does not imply equivalent features.

  • Amazon Nova 2.5 Sonic

    Amazon's generally available real-time speech-to-speech model in Bedrock, with a 256K context window and asynchronous tool calling.

  • Grok Voice 3.0

    xAI's speech-to-speech model in the Voice Agent API, priced at $0.08/min and scoring 86.9 on Artificial Analysis' Speech-to-Speech Index.

  • Helix World

    Real-time interactive world model from Noiz AI and HKUST that generates explorable video with spatial stereo audio from one image.

Browse the Feed