For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundChangelogSign In
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
  • Overview
      • Can I sign up for free?
      • Do my free credits expire?
      • Do you have any type of special pricing for non-profit companies?
      • Do you offer special pricing for start-ups?
      • Do you offer special pricing for YCombinator companies?
      • Do you offer volume discounts?
      • How do I add developers to my account?
      • How do I change my account email address?
      • How do I change the credit card associated with my account?
      • How do I update company information on my invoices?
      • How is multichannel billed?
      • How does the concurrency limit work for transcription requests?
      • How often does the Usage and Spend Information in my Dashboard update?
      • How to share account access with team members
      • Is AssemblyAI available on the AWS Marketplace?
      • What happens if I reach my concurrency limit?
      • What happens when I have used all of my free tier credits?
      • What payment methods do you accept?
LogoLogo
PlaygroundChangelogSign In
On this page
  • Understanding the Concurrency Limit
  • Queue Processing
  • Increasing Your Concurrency Limit
  • Best Practices
OverviewAccount, Billing & Payments

How does the concurrency limit work for transcription requests?

Was this page helpful?
Previous

How often does the Usage and Spend Information in my Dashboard update?

Next
Built with

AssemblyAI’s transcription service for pre-recorded audio uses a concurrency limit to manage the number of simultaneous transcription jobs that can be processed for each account. This article explains how the concurrency limit works and what happens when you reach it.

Understanding the Concurrency Limit

The concurrency limit determines how many transcription jobs can be processed simultaneously for your account. When you submit transcription requests:

  • If you’re below the concurrency limit, your job starts processing immediately.
  • If you’ve reached the limit, additional jobs are placed in a queue.

Queue Processing

When you’ve reached your concurrency limit:

  1. New transcription requests are added to a queue.
  2. As soon as a currently processing job finishes, the next job in the queue starts processing.
  3. This continues until all queued jobs are processed.

The time it takes for queued jobs to start processing depends on the duration of the audio files currently being transcribed.

Increasing Your Concurrency Limit

If you find that the current concurrency limit is insufficient for your needs, you can increase it by upgrading your account. To do this:

  1. Add a credit card to your account.
  2. Choose a plan that offers a higher concurrency limit.

Upgrading your account not only increases your concurrency limit but may also provide additional features and benefits.

Scale to support any workload

We offer custom concurrency limits that scale to support any workload at no additional cost. If you need a higher concurrency limit please either contact our Sales team or reach out to us at support@assemblyai.com.

Best Practices

To optimize your use of the transcription service:

  • Monitor your job queue to anticipate processing times.
  • For time-sensitive transcriptions, consider upgrading your account if you frequently hit the concurrency limit.
  • Batch your transcription requests efficiently to make the most of your current limit.

If you have any questions about your concurrency limit or need assistance with upgrading your account, please contact our support team.