Support TSS / voice / speech
Open
- Dominant language
- TypeScript
- Stars
- 349
- Forks
- 92
- Avg merge
- 3d 10h
- Merged PRs (30d)
- 24
Description
Support generating audio files, similar to image generation
- To start, don't support streaming
- Wrap AI SDK's `generateSpeech` with a similar API that saves audio
- maybe store as `FilePart` (`{ type: "file", data: url | bytes, mimeType: "audio/aac" }`)
Contributor guide
Assessment
This issue has not been assessed yet.