Streaming audio
Open
Nobody has claimed this yet.
enhancement
python
- Dominant language
- Go
- Stars
- 9.5k
- Forks
- 696
- Avg merge
- 7d 19h
- Merged PRs (30d)
- 2
Description
I know that Replicate supports streaming output for LLM's.
Is there any reason this shouldn't be easy to implement for streaming audio?
One very obvious application would be streaming text-to-speech output in near-realtime.
I can imagine a lot of apps being built with that (and that's my intended use-case) - or streaming music with MusicGen, AudioGen, etc.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
This is a high-level proposal for streaming audio, with no files, tests, or entry points identified. Start by reading the linked Replicate streaming documentation and examining how Cog currently handles streaming output; the issue does not define implementation scope or completion criteria.
Written by the indexing model from the issue text.
Assessment
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100