Gladia

API

Speech-to-text API for recorded and real-time audio in 100+ languages

Price: Free credits, then paid
Access: API key

About

Gladia is a speech-to-text API for recorded files and live streams, with code switching across 100+ languages and add-ons such as diarization, translation and summaries. New accounts get 50€ in one-time credit; pay-as-you-go async transcription costs $0.61 per hour.

What you can do with it

Transcribe recorded audio or video files with speaker diarization
Stream live audio over WebSocket for real-time transcripts in voice agents
Translate, summarize or export subtitles from a transcript

Get started

Sign up at app.gladia.io and copy your API key
Use a public audio URL, or upload a file first

Example

curl -X POST "https://api.gladia.io/v2/pre-recorded" \
  -H "x-gladia-key: $GLADIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/audio.mp3", "model": "solaria-1", "diarization": true}'
# Poll GET https://api.gladia.io/v2/pre-recorded/<id> until status is "done"

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: JavaScript/TypeScript, Python
MCP server: None