mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-31 10:28:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

[voice] feat: add managed voice cloning profiles (#10799)

Browse Source 
* feat(ui): add voice library workflow

Give administrators a production-ready flow to record or upload consented reference audio, manage reusable profiles, inspect API usage, discover compatible models, and hand a saved voice directly to text-to-speech.

Assisted-by: Codex:gpt-5

* feat(voice): add managed voice cloning profiles

Make reusable reference voices manageable through the admin API instead of requiring model-directory and YAML edits. Discover compatible installed and gallery models from server-side backend capabilities, retain explicit model configuration controls, and stage saved references for supported backends.

Expose profile management through REST and MCP, document backend-specific behavior, and cover the workflow from profile creation through real Qwen3-TTS synthesis. Harden the agent-job HTTP test against completion racing cancellation.

Assisted-by: Codex:gpt-5

---------

Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
LocalAI [bot]
2026-07-13 09:54:46 +02:00
committed by GitHub
parent b90e1cae73
commit 4056283aa4
70 changed files with 4808 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
backend/python/coqui/backend.py
View File

@@ -79,14 +79,19 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
if self.tts.is_multi_lingual and lang is None:
return backend_pb2.Result(success=False, message=f"Model is multi-lingual, but no language was provided")
# if model is multi-speaker, use speaker_wav or the speaker_id from request.voice
if self.tts.is_multi_speaker and self.AudioPath is None and request.voice is None:
# A path-shaped per-request voice is a cloning reference; otherwise
# preserve Coqui's named-speaker behavior.
request_voice = request.voice if request.voice else ""
speaker_wav = request_voice if os.path.isfile(request_voice) else self.AudioPath
if self.tts.is_multi_speaker and speaker_wav is None and not request_voice:
return backend_pb2.Result(success=False, message=f"Model is multi-speaker, but no speaker was provided")
if self.tts.is_multi_speaker and request.voice is not None:
self.tts.tts_to_file(text=request.text, speaker=request.voice, language=lang, file_path=request.dst)
if speaker_wav is not None:
self.tts.tts_to_file(text=request.text, speaker_wav=speaker_wav, language=lang, file_path=request.dst)
elif self.tts.is_multi_speaker and request_voice:
self.tts.tts_to_file(text=request.text, speaker=request_voice, language=lang, file_path=request.dst)
else:
self.tts.tts_to_file(text=request.text, speaker_wav=self.AudioPath, language=lang, file_path=request.dst)
self.tts.tts_to_file(text=request.text, language=lang, file_path=request.dst)
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
return backend_pb2.Result(success=True)