← All models

Google Cloud STT Chirp 2

Audio Available Full comparison ↗

google-cloud/chirp-2 · by Google · end-to-end-asr · Built on google/universal-speech-model

Pricing — 1 offering(s)

Google Cloud

About this offering: Google Cloud Speech-to-Text Chirp 2: a second-generation universal speech model, built on Google's Universal Speech Model (USM), with 100+ languages and better accuracy on diverse accents and audio conditions. It's delivered through the Speech-to-Text v2 API, with speaker diarisation, word-level timestamps, spoken punctuation, and both streaming and batch transcription. Free tier: 60 minutes a month across all model types.

Chirp 2 (enhanced accuracy)

  • $0.012 / minute Historical 2024-03-01 → 2026-09-19

    Google STT v2 Chirp 2 model. First 60 minutes/month free.

  • $0.016 / minute Current 2026-09-20 → present
    Google now bills Chirp 2 at the single Speech-to-Text v2 "Standard" rate that covers every v2 model…

    Google now bills Chirp 2 at the single Speech-to-Text v2 "Standard" rate that covers every v2 model. $0.016/min applies to the first 500K minutes a month; volume bands step down to $0.01/min (500K–1M), $0.008/min (1M–2M) and $0.004/min (over 2M).

Standard (previous-gen, V1 API, with data logging)

  • $0.006 / minute Historical 2016-03-01 → 2026-09-19

    Google STT v1 standard models. First 60 minutes/month free.

  • $0.016 / minute Current 2026-09-20 → present
    Speech-to-Text v1 API Standard rate with data logging, for the first 500K minutes a month. Without data…

    Speech-to-Text v1 API Standard rate with data logging, for the first 500K minutes a month. Without data logging, the v1 rate is $0.024/min.

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how Google Cloud STT Chirp 2 fits into a cost-aware routing setup

See how →

Capability profile

How Google Cloud STT Chirp 2 rates across core capability dimensions, with the task-level evidence behind each rating.

transcription accuracy Strong

Strong accuracy across diverse accents, audio qualities, and domains. Chirp 2 improves on the original Chirp model especially on noisy and accented audio.

language support Strong

100+ languages with a single model. Quality holds well across major language families.

speaker diarisation Strong

Native speaker diarisation supported via the v2 API. Multi-speaker detection with speaker labels.

real time streaming Strong

Streaming transcription via gRPC bidirectional stream. Interim results and final transcripts supported.

custom vocabulary Moderate

Phrase hints and speech adaptation support for boosting domain-specific terms. Less flexible than Deepgram's Keywords API.

Benchmarks

Benchmark Score Config Source
WER (LibriSpeech) — Google does not publish LibriSpeech WER for Chirp 2 specifically. Internal benchmarks show improvements over Chirp 1 on diverse audio. —

Operator guidance

Best for teams in the Google Cloud ecosystem needing broad language coverage (100+ languages). At $0.012/min ($0.72/hr) it is cheaper than Azure ($1.00/hr) and Amazon Transcribe ($1.44/hr) but more expensive than Deepgram Nova-3 ($0.26/hr batch) and Universal-2 ($0.15/hr). The free tier (60 minutes/month) is useful for development. Choose Deepgram for the best streaming latency; Universal-2 for the lowest batch cost.

Use cases

Limitations

Citations