Voxtral
Voxtral models are state-of-the-art speech understanding models, which are available in two sizes — a 24B variant for production-scale applications and a 3B variant for local and edge deployments. Both versions are released under the Apache 2.0 license.
Cost / License
- Freemium
- Open Source
Application type
EUPlatforms
- Hugging Face
- Self-Hosted
- Online
Features
- Ad-free
- AI-Powered
- speech transcription
- Speech Recognition
Tags
- ai-model
- mistral-ai
- mistral
- ai-transcription
- open-weights
Voxtral News & Activities
Recent News
- POX published news article about Voxtral
Mistral introduces Voxtral, its first family of open source speech understanding AI modelsMistral has introduced Voxtral, a new family of state-of-the-art speech understanding AI models. Th...
Recent activities
POX added Voxtral as alternative to TranscribeX- NEOcortex liked Voxtral
POX added Voxtral as alternative to Hermes Voice
POX added Voxtral as alternative to Scriber Pro
POX added Voxtral as alternative to Transcriboar
Voxtral information
Developed by
Mistral AI Licensing
Open Source (Apache-2.0) and Freemium product.Pricing
free version with limited functionality.Alternatives
75 alternatives listedSupported Languages
- English
What is Voxtral?
Voxtral models are state-of-the-art speech understanding models, which are available in two sizes — a 24B variant for production-scale applications and a 3B variant for local and edge deployments. Both versions are released under the Apache 2.0 license. We have also made both models available on our API, and also provided a highly optimized transcription-only endpoint that delivers unparalleled cost-efficiency.
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.
Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.