Usage limits
To ensure a smooth experience for all users, certain operations have per-account usage limits.
- Concurrency limits for asynchronous operations
- Rate limits for synchronous operations
The usage limits displayed on this page are default values based on your account type. If you already have a paid account and want to further increase your usage limits, contact our Sales team or send an email to our Support team.
Speech-to-Text usage limits
AssemblyAI limits the number of transcriptions being processed at any given time.
| Concurrent transcriptions | 5 | 200 |
If you submit a transcription that would exceed your usage limit, it'll be added to a queue. Queued transcriptions will be processed automatically as previously submitted transcriptions complete.
If your account balance goes below zero, your concurrency limit will be reduced to 1.
If you exceed your concurrency limit, you'll receive an email stating that your transcripts have been throttled. Note that you'll only receive this email once per day.
Streaming Speech-to-Text usage limits
AssemblyAI limits the number of concurrent sessions.
| Concurrent Streaming sessions | N/A* | 100 |
* Streaming Speech-to-Text is only available for paid users.
If you're consistently exceeding the limit of concurrent sessions, first make sure that you're terminating sessions properly.
- If you're using the WebSocket API directly, you need to send a
terminate_sessionmessage. - If you're using one of the SDKs, consult the docs for the specific SDK you're using.
LeMUR usage limits
LeMUR requests are rate limited within a 60-second time window. For more information, see Rate limits.
| Requests per minute | N/A* | 30 |
* LeMUR is only available for paid users.