Chirp 3 Transcription (Google Cloud Speech-to-Text)
Private preview 2025-04-11, public preview 2025-08-29, GA 2025-10-13 (US/EU multi-region). No word-level timestamps or word confidence. For developers, Gemini 3.5 Transcribe (2026-08-26) claims 70% faster time-to-final than Chirp 3.
- Input
- audio
- Output
- text
- License
- proprietary
- Pricing
- per minute: $0.016 (USD per minute, Speech-to-Text V2 standard recognition, first 500K min/month (tiers down to $0.004/min above 2M min)) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Google Cloud Speech-to-Text API V2 | chirp_3 | https://speech.googleapis.com/v2 (Recognize, StreamingRecognize, BatchRecognize) | docs |
Notable capabilities (1)
- Multilingual ASR with language-agnostic mode: ~100+ languages/locales (about 20 GA), language_codes=['auto'] for language-agnostic transcription, diarization in ~15 languages, speech adaptation. source
Sources: Chirp 3 docs, STT release notes, pricing.