Review · Software & AI
Google Cloud Speech-to-Text review
Google Cloud's speech recognition API with Chirp and task-specific models, billed per second inside Google Cloud.
By the DBotMaker research desk · Updated November 7, 2026
- Capabilities (40%)
- 8.5
- Ease of setup (30%)
- 7.4
- Value (30%)
- 7.6
Google Cloud Speech-to-Text gives you a set of recognition models behind one API: Chirp, the default and latest models, and task-tuned options such as phone_call and video, plus medical conversation and dictation models. It supports 85+ languages and variants, speaker diarization, model adaptation for custom vocabulary, automatic punctuation and language detection. Standard recognition costs $0.016 per minute for the first 500,000 minutes a month and $0.01 per minute after that, with deeper discounts at higher tiers, and the first 60 minutes each month are free. Requests round up to the nearest second. New Google Cloud customers also get $300 in general credits. The trade-off is effort and price: you need a Cloud project, billing and service accounts, and the starting rate is several times what AssemblyAI or Speechmatics charge. Google does not publish a single streaming latency figure on the product page.
Who it is for
Teams already on Google Cloud that want a free monthly allowance and tiered volume pricing.
Price
First 60 minutes a month free; standard recognition $0.016 per minute up to 500,000 minutes, lower at higher volumes; new customers get $300 in Google Cloud credits.
$0.016 / 1 minute, per 1 month / account
Quoted from the vendor pricing page on November 7, 2026.
Key features
- Transcription in 85+ languages and variants
- Standard models including Chirp, phone_call, video and latest_long
- Medical conversation and dictation models
- Speaker diarization and model adaptation
- Automatic punctuation and multilingual language detection
Strengths and weaknesses
- Strength: 60 free minutes every month
- Strength: Rates drop at higher volumes, to $0.01 per minute above 500,000 minutes
- Strength: Requests round up to the nearest second
- Weakness: $0.016 per minute is high compared with specialist APIs
- Weakness: Setup needs a Google Cloud project, billing and service accounts
- Weakness: No published latency figure for streaming
Key facts
- Free tier: First 60 minutes a month
- Languages: 85+ languages and variants
- Billing: Rounded up to the nearest second
Where it ranks
Google Cloud Speech-to-Text is No. 9 in our Best Speech-to-Text APIs verdict.
Alternatives we scored
- AssemblyAI9.1
- Deepgram9.0
- Speechmatics8.8
- ElevenLabs Scribe8.7
Visit cloud.google.com · Questions or corrections: editorial@dbotmaker.io