molefrog / molefrog/moi

Add voice dictation to the chat composer

Open
#103 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
169
Forks
12
Avg merge
1d 19h
Merged PRs (30d)
23

Description

It would be useful to have a microphone button in the chat composer, similar to the dictation button in Codex.

The flow I have in mind:

  • press the mic button and speak
  • stop recording
  • put the transcript into the current draft instead of sending it immediately
  • let the user edit it before sending

This would make longer prompts much easier to enter. Clear recording, permission, and transcription error states would also help.

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

No files or tests are named in the issue. Start by locating the chat composer and its draft-handling entry point, then inspect how input permissions and errors are represented; done means a microphone control can record, place the transcript into the editable draft, and expose recording, permission, and transcription errors without sending automatically.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
audio-video-rtc, frontend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.