Transcribe audio

AssemblyAI

Speech-to-text API that transcribes recorded and live audio into text with word timestamps, speaker labels and analysis options.

Rate limits

Parallel transcriptions, free: 514
Parallel transcriptions, paid: 200+; extra jobs are queued14
New streaming sessions per minute, free: 515
New streaming sessions per minute, paid: 200 to start; rises 10% per minute at 80% use15
New streaming sessions per minute, paid (other page): 1001
HTTP requests: 20,000 per five minutes per account; over the limit returns 40314
Polling one transcript: 60 requests per minute per API key and transcript; over the limit returns 42914

Other limits

Duration per file: 160 ms to 10 hours10
Upload size: 2.2 GB for a local file sent to /v2/upload13
Streaming session length: Auto-closes after 3 hours11

Read from AssemblyAI’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/assemblyai.md