autoEdit 3 - user manual
HomeGithub
1.0.8
1.0.8
  • Introduction
  • Support the project
  • App Release link
  • Installing
    • Installing on Mac OSX
    • Installing on Linux
    • Installing on Windows
  • Uninstalling
  • Initial Setup
  • Speech to text options
    • assemblyAi
    • Speechmatics
    • Mozilla DeepSpeech
    • Pocketsphinx
  • Projects
    • Create a new project
    • Edit a project
    • Delete a project
  • Transcriptions
    • Create a new transcription
      • Working with MXF files
    • Correct the text of a transcription
    • Export options
    • Advanced - working with existing transcripts
  • Paperediting
    • Create a new paper edit
    • Highlight Transcriptions
      • Create custom labels
      • Highlight using custom labels
    • Search
      • Search within one transcript
      • Search across transcripts in a project
    • Add text from a transcript
      • Move the insert point
    • Add headings to your story
    • Reorganize selections
    • Delete
    • Preview
  • Export (options)
    • Opening EDL in video editing software
      • Adobe Premiere
      • Davinci Resolve - 15
      • Final cut pro X
    • Export an video or audio preview
  • Reporting issues
  • Digital Paper Edit - Adobe Panel
    • Install
    • import media
    • Transcription to source monitor
    • Transcription export selections
    • Paper-edit to sequence
Powered by GitBook
On this page

Was this helpful?

  1. Speech to text options

assemblyAi

PreviousSpeech to text optionsNextSpeechmatics

Last updated 5 years ago

Was this helpful?

  • sign up to at

  • 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

  • copy and paste into the app's settings under AssemblyAI.

  • 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.

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.

From assemblyAI's docs
AssemblyAI
assemblyai.com/login/
AssemblyAI settings