Voxtral Mini Transcribe 3

Voxtral TTS 3

Generate multilingual speech with preset voices or a per-request MP3 or WAV voice reference. Supports inline emotion and pace tags, pronunciation hints, and MP3, WAV, PCM, FLAC, or Opus output. Up to 4,000 input characters; returns completed audio.

Voxtral Small Transcribe 3

Transcribe recorded speech with automatic language detection, segment timestamps, and optional speaker diarization. Accepts recordings up to 10 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Returns a completed transcript; word timestamps and translation are unavailable.

GPT-4o Mini Transcribe

OpenAI's efficient speech-to-text model with improved accuracy over Whisper

GPT-4o Mini Transcribe (2025-03-20)

Original release snapshot of GPT-4o Mini Transcribe

GPT-4o Mini Transcribe (2025-12-15)

Latest snapshot of GPT-4o Mini Transcribe with improved accuracy

Voxtral Small 24B

Mistral AI’s original Voxtral Small 24B transcribes recorded speech in English, French, German, Spanish, Italian, Portuguese, Dutch, and Hindi, with automatic language detection. Add a context prompt for names or terminology. Accepts MP3, WAV, FLAC, OGG, and M4A recordings up to 10 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Returns a completed JSON transcript without timestamps, speaker diarization, or translation.