mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-04-29 03:24:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(tts): add support for streaming mode (#8291)

Browse Source 
* feat(tts): add support for streaming mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Send first audio, make sure it's 16

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2026-01-30 11:58:01 +01:00
committed by GitHub
parent 2c44b06a67
commit 68dd9765a0
13 changed files with 369 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/content/features/text-to-audio.md
View File

@@ -29,6 +29,41 @@ curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
Returns an `audio/wav` file.
## Streaming TTS
LocalAI supports streaming TTS generation, allowing audio to be played as it's generated. This is useful for real-time applications and reduces latency.
To enable streaming, add `"stream": true` to your request:
```bash
curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
"input": "Hello world, this is a streaming test",
"model": "voxcpm",
"stream": true
}' | aplay
```
The audio will be streamed chunk-by-chunk as it's generated, allowing playback to start before generation completes. This is particularly useful for long texts or when you want to minimize perceived latency.
You can also pipe the streamed audio directly to audio players like `aplay` (Linux) or save it to a file:
```bash
# Stream to aplay (Linux)
curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
"input": "This is a longer text that will be streamed as it is generated",
"model": "voxcpm",
"stream": true
}' | aplay
# Stream to a file
curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
"input": "Streaming audio to file",
"model": "voxcpm",
"stream": true
}' > output.wav
```
Note: Streaming TTS is currently supported by the `voxcpm` backend. Other backends will fall back to non-streaming mode if streaming is not supported.
## Backends