mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 18:09:05 -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

20
backend/python/fish-speech/backend.py
View File

@@ -267,6 +267,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
def _get_ref_audio_path(self, voice_name=None):
"""Get reference audio path from voices dict or stored AudioPath."""
if voice_name and os.path.isfile(voice_name):
return voice_name
if voice_name and voice_name in self.voices:
audio_path = self.voices[voice_name]["audio"]
@@ -332,7 +334,19 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
references = []
voice_name = request.voice if request.voice else None
if voice_name and voice_name in self.voices:
if voice_name and os.path.isfile(voice_name):
ref_audio_path = self._get_ref_audio_path(voice_name)
with open(ref_audio_path, "rb") as f:
audio_bytes = f.read()
ref_text = request.params.get("ref_text", "") if hasattr(request, "params") else ""
references.append(
ServeReferenceAudio(audio=audio_bytes, text=ref_text)
)
print(
f"[INFO] Using per-request reference audio: {ref_audio_path}",
file=sys.stderr,
)
elif voice_name and voice_name in self.voices:
ref_audio_path = self._get_ref_audio_path(voice_name)
if ref_audio_path and os.path.exists(ref_audio_path):
with open(ref_audio_path, "rb") as f:
@@ -350,7 +364,9 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
if ref_audio_path and os.path.exists(ref_audio_path):
with open(ref_audio_path, "rb") as f:
audio_bytes = f.read()
ref_text = self.options.get("ref_text", "")
ref_text = request.params.get("ref_text", "") if hasattr(request, "params") else ""
if not ref_text:
ref_text = self.options.get("ref_text", "")
references.append(
ServeReferenceAudio(audio=audio_bytes, text=ref_text)
)