Introducing the world's best (and open) speech recognition models!

Both Voxtral 3B and Voxtral 24B models go beyond transcription with capabilities that include: · Long-form context: with a 32k token context length, Voxtral handles audios up to 30 minutes for transcription, or 40 minutes for understanding · Built-in Q&A and summarization: Supports asking questions directly about the audio content or generating structured summaries, without the need to chain separate ASR and language models · Natively multilingual: Automatic language detection and state-of-the-art performance in the world’s most widely used languages (English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian, to name a few), helping teams serve global audiences with a single system · Function-calling straight from voice: Enables direct triggering of backend functions, workflows, or API calls based on spoken user intents, turning voice interactions into actionable system commands without intermediate parsing steps. · Highly capable at text: Retains the text understanding capabilities of its language model backbone, Mistral Small 3.1