supermarket

Transcribe audio

Google Cloud Speech-to-Text

Speech recognition API on Google Cloud that returns transcripts from audio files or live streams.

At a glance

Provider
Google Cloud
Category
Transcribe audio
Type
Hosted API
Pricing model
Pay as you go per second of audio, with monthly volume tiers per account1
Free tier
60 minutes a month on the V1 API; the V2 price table lists none1
Authentication
Google Cloud IAM: Application Default Credentials, user credentials or service accounts8
Connect via
REST API (V1, V2), gRPC, client libraries, Google Cloud console8
Read from the provider's pages
2026-11-04
Pricing
  • Pricing model: Pay as you go, billed per second of audio processed, with monthly tiers per account
  • Free tier: 60 minutes a month on the V1 API; the V2 price table lists no free tier
  • Free tier (new customers): $300 in Google Cloud free credits for new customers
Pricing in full →Tools
  • Official MCP server: No
  • Address or package: None found: no mention in the Speech-to-Text docs pages read, and no result for speech and mcp in the googleapis or GoogleCloudPlatform GitHub orgs
Tools in full →Authentication
  • Who creates the account: A person signs in to a Google Cloud account and selects or creates a project; agent sign-up is not stated
  • Where to get a key: No API key shown; credentials come from IAM (ADC, user or service account) via the gcloud CLI or the Google Cloud console
  • Other requirements: A Google Cloud project with billing enabled, and the Speech-to-Text API enabled
Authentication in full →Setup
  • REST API: https://speech.googleapis.com; regional https://us-speech.googleapis.com and https://eu-speech.googleapis.com
  • MCP server: None found
  • OpenAPI spec: Google Discovery documents (not OpenAPI): https://speech.googleapis.com/$discovery/rest?version=v2
Setup in full →Limits
  • Streaming: Each stream message up to 25 KB of audio; stream open up to 5 minutes
  • Batch: Up to 5 files per request, each up to 8 hours; Cloud Storage only
  • Phrases per request: 5,000 phrases and 100,000 characters in adaptation
Limits in full →Privacy
  • Data location: Processed globally; US or EU multi-region endpoints limit processing to those regions; single region not supported
  • Retention: Sync and streaming audio processed in memory; async transcripts stored about 5 days; input audio not stored
  • Used for training: Only for customers who opted in to data logging
Privacy in full →

Read from Google Cloud’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/google-cloud-speech-to-text.md