# Google Cloud Speech-to-Text (slim)

> Google Cloud's transcription API.

- Full: https://www.anchorterminal.com/tools/google-speech-to-text.md (~6,400 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/google-speech-to-text.json · canonical https://www.anchorterminal.com/tools/google-speech-to-text
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 70.4/100 · rank #98 of 452 · #4 in Speech-to-text · agent-ready · confidence medium**


Assessment: Audio isn't stored or used for training unless the project opts in to data logging. No release note since 2025-11-13.

## Facts

- Kind: Model API · vendor: Google Cloud · category: Speech-to-text · legal entity: Google LLC · provenance 100/100
- Endpoint: `https://speech.googleapis.com/v2` (HTTP)
- Auth: OAuth · pricing: Freemium · x402: no · licence: Apache-2.0 (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: `chirp_3` (GA in `us` and `eu`), `chirp_2`, `chirp`, plus `latest_long`, `latest_short`, `telephony` and the medical models
- Languages: Chirp 3 has 29 locales GA and 82 in preview, 111 in total
- Modes: `StreamingRecognize` (real time), `Recognize` (up to 1 minute or 10 MB), `BatchRecognize` (files in Cloud Storage, up to 8 hours each)
- Streaming latency: No published figure. Streams must be sent at roughly real time and last up to 5 minutes
- Diarisation: Chirp 3 in batch and sync only, for 16 locales
- Other options: Speech adaptation (phrase biasing), built-in denoiser, custom prompt (preview). Chirp 2 adds speech translation
- Free tier: 60 minutes a month on V1. The V2 price table lists no free minutes. New accounts get $300 credit
- Rate limits: 300 concurrent streaming sessions, 300 sync and 150 batch requests a minute per region, per project
- Data retention: Streaming and sync audio is processed in memory and not stored. Batch transcripts are kept about 5 days. No training use unless data logging is on
- Data residency: `us` and `eu` multi-region endpoints. Single-region pinning isn't supported
- Prices: V2 standard recognition (Chirp 3) $0.016 per minute of audio; V2 standard recognition over 2M minutes $0.004 per minute of audio; V2 dynamic batch $0.003 per minute of audio; V1 without data logging $0.024 per minute of audio; Medical models $0.078 per minute of audio

- Scores: Reliability 85, Performance pending, Schema & documentation 80, Agent ergonomics 70, Security & auth 95, Payments & pricing 20, Task success pending, Maintenance & community 25, Transparency & trust 88 · total over the 7 assessed categories
- Why: Reliability, Google Cloud status page with a per-product history (20). · Schema & documentation, The API surface is public as protocol buffers and a discovery document, a machine-readable contract (25). · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The newest release note is 2025-11-13, Chirp 3 preview in four more regions, 322 days ago (0). · Transparency & trust, Closed service under the Google Cloud terms (15).
- Sources: 7, open questions: 2, both in the full twin
- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation
- JSON: https://www.anchorterminal.com/api/v1/tools/google-speech-to-text.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/google-speech-to-text.svg` or a link to https://www.anchorterminal.com/tools/google-speech-to-text from a page on google.com or one of its subdomains, or the README of github.com/googleapis/google-cloud-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Call Chirp 3 on the `us` or `eu` endpoint. It isn't listed for the `global` location
2. Reopen streams before the 5-minute limit, or use `BatchRecognize` for recordings
3. Downmix stereo unless you need channel labels, since each channel is billed
4. Set dynamic batch on offline jobs to cut the price from $0.016 to $0.003 a minute
5. Back off on `RESOURCE_EXHAUSTED`. The Speech docs don't give a retry interval

## Connect

```bash
pip install google-cloud-speech   # or: npm i @google-cloud/speech
```

```bash
curl -X POST "https://us-speech.googleapis.com/v2/projects/$GOOGLE_CLOUD_PROJECT/locations/us/recognizers/_:recognize" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "content-type: application/json" \
  -d '{"config":{"model":"chirp_3","languageCodes":["en-US"],"autoDecodingConfig":{}},"uri":"gs://cloud-samples-data/speech/brooklyn_bridge.flac"}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Azure AI Speech speech-to-text | BB | 77 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md |
| Gladia Speech-to-Text API + MCP | B | 69.7 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/gladia-stt.min.md |
| Speechmatics Speech-to-Text | B | 67.3 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/speechmatics-stt.min.md |
| AssemblyAI Speech-to-Text (Universal) | B | 67 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/assemblyai-stt.min.md |
| Soniox Speech-to-Text | C | 58.3 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/soniox-stt.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ Sixteen dollars per 1,000 minutes, and stereo bills twice (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ Numeric quotas, no word on what a breach returns (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)