mudler / mudler/LocalAI

Streaming TTS support for other backends

Open
#9,051 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement roadmap
Dominant language
Go
Stars
49.2k
Forks
4.5k
Avg merge
1d 3m
Merged PRs (30d)
239

Description

Is your feature request related to a problem? Please describe.
Trying to get streaming TTS on qwen3-tts and it runs on the backend rocm-qwen-tts. but voxcpm is the only backend that currently supports streaming TTS so can't use streaming TTS even though the model/backend supports it

Describe the solution you'd like
Streaming TTS enabled for all backends that are able to do it

Describe alternatives you've considered
None

Additional context
https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen3_tts#streaming-mode

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the existing voxcpm streaming TTS implementation and comparing it with qwen3-tts and rocm-qwen-tts. Use the linked vLLM-omni streaming-mode example to understand the backend capability, then identify how LocalAI exposes streaming support. Done means streaming TTS works for every capable backend without enabling it for unsupported backends.

Written by the indexing model from the issue text.

Assessment

Tech stack
go
Domain
audio-video-rtc, backend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.