Voxtral 3
Voxtral 3 is Mistral AI's voice agent stack: speech-to-text in 50+ languages with speaker labels and end-of-turn detection, expressive text-to-speech in 35+ languages, and a voice agent SDK built on LiveKit that handles listening, tool calls and speaking in one stream over SIP or WebRTC. You can use it through Mistral's API with EU, US or global endpoints, or deploy it yourself, and it is priced per minute of audio or per character.
Updated
✨ Try AgentScout's free AI image generator →Good for: building AI agents, building voice agents
Official channels
Use cases
About Voxtral 3
Voxtral 3 is listed in our voice category and is aimed at builders. Voxtral 3 is Mistral AI's voice agent stack: speech-to-text in 50+ languages with speaker labels and end-of-turn detection, expressive text-to-speech in 35+ languages, and a voice agent SDK built on LiveKit that handles listening, tool calls and speaking in one stream over SIP or WebRTC. You can use it through Mistral's API with EU, US or global endpoints, or deploy it yourself, and it is priced per minute of audio or per character. Pricing, as the maker states it: Transcription from $0.0035/min, TTS $13 per 1M characters, voice agent API from $0.04/min. Maturity: Active. We last checked the official link on 2026-10-22.
Voxtral 3 at a glance
- Category: Voice
- Built for: Developers and teams building with AI agents
- Pricing: Transcription from $0.0035/min, TTS $13 per 1M characters, voice agent API from $0.04/min (as the maker states it)
- Official site: mistral.ai/news/voxtral-3
- Listed on AgentScout: Oct 22, 2026
Voxtral 3 FAQ
What is Voxtral 3?
Voxtral 3 is Mistral AI's voice agent stack: speech-to-text in 50+ languages with speaker labels and end-of-turn detection, expressive text-to-speech in 35+ languages, and a voice agent SDK built on LiveKit that handles listening, tool calls and speaking in one stream over SIP or WebRTC. You can use it through Mistral's API with EU, US or global endpoints, or deploy it yourself, and it is priced per minute of audio or per character.
How much does Voxtral 3 cost?
Voxtral 3's pricing, as the maker states it: Transcription from $0.0035/min, TTS $13 per 1M characters, voice agent API from $0.04/min. Check the official site for current plans.
What are alternatives to Voxtral 3?
Similar tools include Deepgram, Speechmatics, Cartesia Sonic, Dial, Qwen Audio Agent and Fish Audio.
Facts from our link-checked listing and the official site. See something wrong? Suggest an edit.
Voxtral 3 ratings and reviews
Be the first to rate Voxtral 3: tap 1 to 5 stars below. A written review is optional.
Voxtral 3 alternatives
Other voice tools in our directory. See all voice tools →
Deepgram
Speech-to-text, text-to-speech and voice agent APIs for building real-time voice agents.
Speechmatics
Speech-to-text and voice AI APIs that handle accents, multiple speakers and multilingual speech for voice agents.
Cartesia Sonic
Cartesia's real-time text-to-speech API with emotion control, built for low-latency voice agents.
Dial
Gives an AI agent a real phone number for calls, SMS, iMessage and WhatsApp through one API.
Qwen Audio Agent
Real-time voice runtime from the Qwen Audio team that keeps agents talking while they think and work on tasks.
Fish Audio
Fish Audio is a voice AI platform for text to speech, voice cloning and speech to text, with a real-time API for voice agents. Its Drama 3 and S2 models take inline emotion and delivery tags such as whispering, laughing or pauses, it can clone a voice from a few seconds of audio, and its library has more than two million community voices for narration, characters, audiobooks and support agents. The Fish Speech models behind it are published on GitHub and Hugging Face.
Related lists
🏆 See also: Best AI Voice Agent Platforms · All best-of lists
🧭 Task guides: Voice and phone agents for building AI agents
Badge for makers
Built Voxtral 3? Add this badge to your README or site. It links back to this page. About badges
