feat: Support custom Whisper API endpoints for voice transcription #2634
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
|
mbailey
force-pushed
the
feat/allow-use-of-other-whisper-api-endpoints-take-2
branch
from
617b359 to
5911c51
Compare
This was referenced Dec 15, 2024
mbailey
force-pushed
the
feat/allow-use-of-other-whisper-api-endpoints-take-2
branch
2 times, most recently
from
e3d656c to
110094b
Compare
|
I rewrote it and force pushed. I've updated the PR description to reflect that it now follows Aider conventions for handing API keys and env vars. |
mbailey
force-pushed
the
feat/allow-use-of-other-whisper-api-endpoints-take-2
branch
2 times, most recently
from
10120d8 to
b9ad3eb
Compare
This change adds the ability to use alternative Whisper API providers for voice transcription, while maintaining backwards compatibility with the default OpenAI endpoint. - Added support for custom Whisper API endpoints via `WHISPER_API_BASE` and `WHISPER_API_KEY` environment variables - Updated the voice transcription logic to handle both custom and OpenAI endpoints - Added validation to require a specific API key when using custom endpoints - Updated documentation to explain the new configuration options - Added new test cases to verify API endpoint and key handling - When using a custom Whisper endpoint (`WHISPER_API_BASE`): - Must provide a corresponding `WHISPER_API_KEY` - OpenAI API key will not be used - When using default OpenAI endpoint: - Will use `WHISPER_API_KEY` if provided - Falls back to `OPENAI_API_KEY` if no Whisper-specific key is set - Added configuration examples in the optional installation docs - Updated voice coding documentation to reference the new features - Added new environment variables to the sample.env file This change enables users to: - Use alternative Whisper API providers - Run Whisper locally or on their own infrastructure - Better control costs and data privacy for voice transcription
mbailey
force-pushed
the
feat/allow-use-of-other-whisper-api-endpoints-take-2
branch
from
b9ad3eb to
930a652
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add support for custom Whisper API endpoints
2024-12-18: Third rewrite - more compatible with existing conventions for handling API keys
This PR adds the ability to use alternative Whisper API providers for voice transcription, while maintaining backwards compatibility with the default OpenAI endpoint.
Key Changes
WHISPER_API_BASEandWHISPER_API_KEYenvironment variablesAPI Key Behavior
WHISPER_API_BASE):WHISPER_API_KEYWHISPER_API_KEYif providedOPENAI_API_KEYif no Whisper-specific key is setDocumentation Updates
This change enables users to: