Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

OpenAI key should not be required for voice mode #1341

Open
tianshuo opened this issue Sep 4, 2024 · 3 comments
Open

OpenAI key should not be required for voice mode #1341

tianshuo opened this issue Sep 4, 2024 · 3 comments
Labels
enhancement New feature or request

Comments

@tianshuo
Copy link

tianshuo commented Sep 4, 2024

Issue

aider 0.54.12
macOS

Run /voice
Outputs: To use /voice you must provide an OpenAI API key.

This is hardcoded in the source code, but actually, we can support:

  1. Local Fast-whisper
  2. Groq has whisper too.
  3. Other third-parties have speech recognition too.

This feature shouldn't be hard to implement, we should support non-OpenAI speech recognition suppliers.

Version and model info

No response
@paul-gauthier paul-gauthier added the enhancement New feature or request label Sep 4, 2024
@au-to-pi-lot
Copy link

I was just checking out the voice mode documentation and realized that local voice to text would be really useful. Seconded!

@daviddahl
Copy link

I am using Azure OpenAI and still get this error.

@mbailey
Copy link

mbailey commented Dec 15, 2024

Solved by #2634

This was my Sunday. :-)

Feel free to test with Whisper running on my M4 Mac Mini:

openai-api-base-whisper=https://api.ailocal.org/
openai-api-key-whisper=sk-aider-xmas

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
5 participants
@mbailey @daviddahl @tianshuo @au-to-pi-lot @paul-gauthier