Chirp 3

Voxtral Small Transcribe 3 is a multilingual speech-to-text model for transcribing recorded audio. Mistral provides it through an audio transcription API and documents timestamps, speaker diarization, and context biasing, which allows developers to supply key phrases to help recognize domain-specific terms and names. The model automatically detects supported languages or accepts a language code, and supports more than 50 languages. It is designed for application developers building recorded-audio workflows, including meeting, interview, and call transcription, customer-service systems, and voice-agent pipelines. Mistral also describes self-deployment options for the Voxtral 3 family, including private-cloud and on-premises hosting.

Gemini 3.5 Transcribe is Google’s most precise speech-to-text model yet, designed for intelligent voice interactions and real-time transcription. Instead of simply converting speech word for word, it turns raw audio into accurate, polished, formatted text while handling background noise, complex jargon, accents, dialects, and natural speaking patterns. Smart transcription automatically understands self-corrections, removes filler words such as “ums” and “ahs,” and formats the final text for readability. The model supports continuous bidirectional streaming with sub-second latency for interactive voice applications, as well as pre-recorded audio processing for meetings, call logs, and other recordings with speaker attribution and word-level timestamps. Custom vocabulary helps it recognize specialized terminology, unique spellings, postal codes, order IDs, and other domain-specific language.