> For the complete documentation index, see [llms.txt](https://autoedit.gitbook.io/autoedit-3-user-manual/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://autoedit.gitbook.io/autoedit-3-user-manual/1.0.8-1/speech-to-text/assemblyai.md).

# assemblyAi

* sign up to [AssemblyAI](https://www.assemblyai.com) at [assemblyai.com/login/](https://www.assemblyai.com/login/)
* Once you have logged in /signed up. in the top left you'll see `Your API Token`
* Select and copy that string of letters and digits&#x20;
* copy and paste into the app's settings under `AssemblyAI`.&#x20;
* `Save`.

## Language preferences

Once you set your credentials as above, you also have options to choose between different English accents, and whether you'd want to use a language model or stick with the default.

![AssemblyAI settings](https://1331059686-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LzxDa5M0ZjC8OZg1Atb%2F-M5U0WafT4T8-kGcuXH5%2F-M5U0zeoB0faCQ0s0Vp8%2Fassemblyai-language-preferences.png?alt=media\&token=268945b4-9665-462c-af8d-b6eb551ca331)

[From assemblyAI's docs](https://docs.assemblyai.com/overview/custom-models)

> `default` language model Best for conversational data like phone calls and meetings.

> `Media` language model is best for broadcast news and radio and at recognizing proper nouns, this model has a much larger vocabulary than the default model.
