Mistral AI unveils Voxtral, an innovative suite of open source speech understanding models designed to transform human-machine interaction through voice. Viewing voice as humanity's original interface, Voxtral aims to move beyond the limitations of current systems, whether unreliable or proprietary, by delivering voice tools that are robust, multilingual, and deeply intelligent. The models come in two versions: a 24B variant built for production-scale applications, and a more compact 3B variant, Voxtral Mini, suited for local and edge deployments. Both are released under the permissive Apache 2.0 license and accessible via Mistral AI's API, with Voxtral Mini Transcribe, optimized for transcription, delivering unmatched cost/latency efficiency.
Two-tier architecture and cost advantage
Voxtral distinguishes itself by bridging the gap between high-error-rate open source ASR systems and costly proprietary APIs. It delivers state-of-the-art accuracy and native semantic understanding in an open framework, at less than half the price of comparable proprietary solutions. This cost efficiency makes high-quality, controllable voice intelligence accessible at scale for a wide range of applications.
Advanced capabilities beyond transcription
The models offer several advanced capabilities beyond simple transcription. They support long audio contexts, up to 30 minutes for transcription and 40 minutes for understanding, enabling the complete processing of extended conversations or recordings. A standout feature: built-in Q&A and summarization, which allow direct querying of audio content or generation of structured summaries without chaining separate ASR and language models. Voxtral is natively multilingual, with automatic language detection and state-of-the-art performance across numerous widely used languages: English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian. It also enables function-calling directly from voice, translating users' spoken intentions into actionable system commands. The models retain the strong text understanding capabilities of their base, the Mistral Small 3.1 language model.
Competitive benchmarks
Benchmark results highlight Voxtral's superior performance. It outperforms Whisper large-v3 overall, the reference open source transcription model, and surpasses GPT-4o mini Transcribe and Gemini 2.5 Flash on various tasks. Voxtral Small achieves state-of-the-art on short-form English and Mozilla Common Voice, demonstrating strong multilingual capabilities, and matches ElevenLabs Scribe for premium use cases at a significantly lower cost. Voxtral Mini Transcribe outperforms OpenAI Whisper at less than half the price.
Roadmap and vision
Mistral AI plans to introduce speaker segmentation, audio annotations (age, emotion), word-level timestamps, and non-speech audio recognition. The company is growing its audio team and encourages developers to integrate Voxtral via local download on Hugging Face, via the API, or by trying it in Le Chat's voice mode, with advanced enterprise features: private deployment, domain-specific fine-tuning, and dedicated integration support.