Transcribe audio
Gladia
Speech-to-text API for pre-recorded and live audio that returns transcripts with timestamps, speaker labels and optional add-ons.
At a glance
- Provider
- Gladia
- Category
- Transcribe audio
- Type
- Hosted API
- Pricing model
- Prepaid credit wallet, billed per hour of audio1
- Free tier
- EUR 50 in credits, one time, valid for one year1
- Authentication
- API key in the
x-gladia-keyheader3 - Connect via
- REST API, WebSocket, JavaScript and Python SDKs, CLI, local MCP server16
- Read from the provider's pages
- 2026-11-04
Pricing
- Pricing model: Prepaid credits with no subscription; pay for the audio processed
- Free tier: EUR 50 in credits, one time, valid for one year; free accounts get 3 concurrent pre-recorded jobs and 1 live session
- Card required for free tier: Not published
- Official MCP server: Yes, local
- Address or package:
@gladiaio/mcpon npm, run withnpx -y @gladiaio/mcp; source in thegladiaio/gladia-mcpGitHub repository
- Who creates the account: A person signs up at app.gladia.io (Google sign-in); sign-up by an agent alone is not described
- Where to get a key: API keys section of app.gladia.io; a default key is created at sign-up
- Other requirements: Not published
- REST API:
https://api.gladia.io/v2/pre-recorded - MCP server: No hosted address; local stdio server run with
npx -y @gladiaio/mcp - OpenAPI spec:
https://api.gladia.io/openapi.json
- Pre-recorded audio length: 135 minutes per request; 4h15 on Enterprise
- Pre-recorded file size: 1000 MB
- Live session length: 3 hours per session
- Data location: EU and US workloads are kept separate on region-specific infrastructure; HDS hosting for enterprise
- Retention: Paid accounts: audio and transcripts 3 weeks, request metadata 1 year. Free accounts: all data 1 year. Enterprise can set a custom period
- Used for training: Self-serve: opted in by default, free opt-out from the profile; Enterprise: opted out by default
Read from Gladia’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/gladia.md