Skip to content

feat: convert CAF audio and GIF attachments for model compatibility#73

Open
mfzeidan wants to merge 1 commit intosteipete:mainfrom
mfzeidan:main
Open

feat: convert CAF audio and GIF attachments for model compatibility#73
mfzeidan wants to merge 1 commit intosteipete:mainfrom
mfzeidan:main

Conversation

@mfzeidan
Copy link

iMessage voice messages use Opus-in-CAF format which isn't supported by OpenAI Whisper. GIF images aren't accepted by all model APIs (e.g. xAI). This adds ffmpeg-based conversion: .caf→.m4a for audio, .gif→.png (first frame) for images. Converted files are cached alongside originals.

iMessage voice messages use Opus-in-CAF format which isn't supported by
OpenAI Whisper. GIF images aren't accepted by all model APIs (e.g. xAI).
This adds ffmpeg-based conversion: .caf→.m4a for audio, .gif→.png
(first frame) for images. Converted files are cached alongside originals.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant