microsoft / microsoft/markitdown

[Feature Request] Customized Audio Transcription Provider

Open
#1,275 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
186k
Forks
13.7k
Avg merge
1d 4h
Merged PRs (30d)
49

Description

Current implementation:
https://github.com/microsoft/markitdown/blob/62b72284feb986ffaf8c22fa73614545b5713c30/packages/markitdown/src/markitdown/converters/_transcribe_audio.py#L48

The problem is that, when my audio is not in English, it still try to transcribe to English. Is it possible to implement some configurable options to change to other provider? The SpeechRecognition library provides a couple of alternative. Technically, it should not be hard to implement... The problem is how to make the configuration intuitive and easy to understand...

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with packages/markitdown/src/markitdown/converters/_transcribe_audio.py at the linked implementation. Review how transcription is currently configured and how alternative providers could be exposed; done means users can select a provider or language through an intuitive configuration and non-English audio is handled accordingly.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.