pyannoteAI

Production speech-to-text + audio intelligence API.

Speech recognition API with batch and real-time streaming transcription, speaker diarization, and language detection. Its Universal models pair with optional Speech Understanding features (summarization, sentiment, redaction) so a single API can build conversation-intelligence products. Starts with a free credit and pay-as-you-go, per-second billing.

Production speech-to-text. The STT default for many companies.

End-to-end speech recognition platform — real-time streaming, batch transcription, speaker diarization, and language detection. Strong on accented speech, telephony audio, and long-form recordings.

Real-time speech-to-text and audio intelligence through a single API.

End-to-end audio infrastructure to record, transcribe, and enrich speech via one API — real-time streaming under ~300ms latency, batch transcription, diarization, translation, and summarization across 100+ languages. Reengineered Whisper for production before shipping its own Solaria models, with EU data residency for compliance-bound teams.

Enterprise speech APIs — real-time STT, TTS, and voice agents in 55+ languages.

Speechmatics provides speech-to-text (batch and sub-second real-time), text-to-speech, and a Flow API for building voice agents, with accuracy that holds up across accents and dialects in 55+ languages. The same engine deploys in cloud, container, on-prem, or fully on-device, and it powers products from Adobe, LiveKit, and Ubisoft.