Start now for free

Product improvements

Check out the AssemblyAI changelog to see weekly accuracy and product improvements our team has been working on.

Powering incredible companies


Usage and spend alerts

Users can now set up billing alerts in their user portals. Billing alerts notify you when your monthly spend or account balance reaches a threshold.

To set up a billing alert, go to the billing page of your portal, and click Set up a new alert under the Your alerts widget:

You can then set up an alert by specifying whether to alert on monthly spend or account balance, as well as the specific threshold at which to send an alert.


Universal-1 now available in German

Universal-1, our most powerful and accurate multilingual Speech-to-Text model, is now available in German.

No special action is needed to utilize Universal-1 on German audio - all requests sent to our /v2/transcript endpoint with German audio files will now use Universal-1 by default. Learn more about how to integrate Universal-1 into your apps in our Getting Started guides.


New languages for Speaker Diarization

Speaker Diarization is now available in five additional languages for both the Best and Nano tiers:

  • Chinese
  • Hindi
  • Japanese 
  • Korean 
  • Vietnamese


New API Reference, Timestamps improvements

We’ve released a new version of the API Reference section of our docs for an improved developer experience. Here’s what’s new:

  1. New API Reference pages with exhaustive endpoint documentation for transcription, LeMUR, and streaming
  2. cURL examples for every endpoint
  3. Interactive Playground: Test our API endpoints with the interactive playground. It includes a form-builder for generating requests and corresponding code examples in cURL, Python, and TypeScript
  4. Always up to date: The new API Reference is autogenerated based on our Open-Source OpenAPI and AsyncAPI specs

We’ve made improvements to Universal-1’s timestamps for both the Best and Nano tiers, yielding improved timestamp accuracy and a reduced incidence of overlapping timestamps.

We’ve fixed an issue in which users could receive an `Unable to create transcription. Developers have been alerted` error that would be surfaced when using long files with Sentiment Analysis.


New codec support; account deletion support

We’ve upgraded our transcoding library and now support the following new codecs:

  • HEVC, VP9, AV1 codec in enhanced flv format

Users can now delete their accounts by selecting the Delete account option on the Account page of their AssemblyAI Dashboards.

Users will now receive a 400 error when using an invalid tier and language code combination, with an error message such as The selected language_code is supported by the following speech_models: best, conformer-2. See

We’ve fixed an issue in which nested JSON responses from LeMUR would cause Invalid LLM response, unable to fulfill request. Please try again. errors.

We’ve fixed a bug in which very long files would sometimes fail to transcribe, leading to timeout errors.