Transcribe audio

Gladia

Speech-to-text API for pre-recorded and live audio that returns transcripts with timestamps, speaker labels and optional add-ons.

Rate limits

Exceeding concurrency returns HTTP 429. A separate per-user API request rate limit exists but its number is not published.

Plan	Concurrent pre-recorded jobs	Concurrent live sessions	Queued async requests
Free	3	1	Not stated
Paid	25	30	Up to 300
Enterprise	On demand	On demand	Not stated

Source6API rate limits and transcription concurrency

Other limits

Pre-recorded audio length: 135 minutes per request; 4h15 on Enterprise7
Pre-recorded file size: 1000 MB7
Live session length: 3 hours per session6
Channels: Pre-recorded: up to 2; live: up to 87
API request rate (calls per time frame): Not published

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