As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/chirp-3/

# Chirp 3 Transcription (Google Cloud Speech-to-Text)

Google, Chirp 3 family. Status: current. Type: speech and audio. Released: 2025-10-13.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Google Cloud Speech-to-Text API V2 | `chirp_3` | https://speech.googleapis.com/v2 (Recognize, StreamingRecognize, BatchRecognize) | https://docs.cloud.google.com/speech-to-text/docs/models/chirp-3 |

## Pricing

- Per minute: $0.016
- Unit as published: USD per minute, Speech-to-Text V2 standard recognition, first 500K min/month (tiers down to $0.004/min above 2M min)
- Source: https://cloud.google.com/speech-to-text/pricing
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 81. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Google: Gemini 2.5 Flash Native Audio (Live, preview) (2025-09-23) https://postcutoff.com/m/gemini-2-5-flash-native-audio/
- After it from Google: Gemini 3.1 Flash Live (preview) (2026-03-26) https://postcutoff.com/m/gemini-3-1-flash-live/
- Closed weights; access is hosted only.

## What stands out

- 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: https://docs.cloud.google.com/speech-to-text/docs/models/chirp-3

## Notes

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.

Sources: [Chirp 3 docs](https://docs.cloud.google.com/speech-to-text/docs/models/chirp-3), [STT release notes](https://docs.cloud.google.com/speech-to-text/docs/release-notes), [pricing](https://cloud.google.com/speech-to-text/pricing).

Model page: https://postcutoff.com/m/chirp-3/