Speech to text options

There are three options for speech to text APIs that you can use with this system.

Check them out individually for extra setup instruction.

  1. Mozilla Deep Speech (Open Source, need to download 1.8gig for the English language model)

  2. Pocketsphinx (Open Source, integrate inside the app, no extra setup needed)

Overview

AssemblyAI

  • Free tier: 5 hours free per month

  • Easy to setup credentials

  • Generally very accurate (my opinion, judge for yourself)

  • For now only support for English but more coming soon

Speechmatics

  • 1 hour free credit with new account

  • Easy to setup credentials

  • Generally pretty accurate (my opinion, judge for yourself)

  • Including support for "accent agnostic global english".

Mozilla Deepspeech

Pros:

  • Free as in free speech as well as in free beer.

  • Working locally on your machine. No internet connection needed because of that, good for sensitive material.

  • Open source

  • requires to download 1.8gig for the English language model

Cons:

  • Not as accurate as commercial STT but still pretty good (in my opinion, but decide for yourself).

  • Only support US english STT.

Check out for extra setup instructions for Mozilla Deepspeech .

Pocketsphinx

Pros:

  • Free as in free speech as well as in free beer.

  • working locally on your machine. no internet connection needed because of that, good for sensitive material.

  • Open source module in autoEdit originally extracted from Videogrep project.

Cons:

  • Not as accurate as IBM or Gentle.

  • Only support US english STT.

  • Transcription takes a little longer then the length of the media. (eg 27 min takes 30 min to transcribe).

Pocketsphinx does not require extra setup to use.