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

16
backend/python/voxcpm/backend.py
View File

@@ -144,7 +144,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
if os.path.exists(potential_path):
prompt_wav_path = potential_path
if hasattr(request, 'AudioPath') and request.AudioPath:
if prompt_wav_path is None and hasattr(request, 'AudioPath') and request.AudioPath:
if os.path.isabs(request.AudioPath):
prompt_wav_path = request.AudioPath
elif hasattr(request, 'ModelFile') and request.ModelFile:
@@ -155,8 +155,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
else:
prompt_wav_path = request.AudioPath
# Get prompt_text from options if available
if "prompt_text" in self.options:
# Per-request profile transcript takes precedence over YAML.
if hasattr(request, "params") and request.params.get("ref_text"):
prompt_text = request.params["ref_text"]
elif "prompt_text" in self.options:
prompt_text = self.options["prompt_text"]
# Prepare text
@@ -241,7 +243,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
if os.path.exists(potential_path):
prompt_wav_path = potential_path
if hasattr(request, 'AudioPath') and request.AudioPath:
if prompt_wav_path is None and hasattr(request, 'AudioPath') and request.AudioPath:
if os.path.isabs(request.AudioPath):
prompt_wav_path = request.AudioPath
elif hasattr(request, 'ModelFile') and request.ModelFile:
@@ -252,8 +254,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
else:
prompt_wav_path = request.AudioPath
# Get prompt_text from options if available
if "prompt_text" in self.options:
# Per-request profile transcript takes precedence over YAML.
if hasattr(request, "params") and request.params.get("ref_text"):
prompt_text = request.params["ref_text"]
elif "prompt_text" in self.options:
prompt_text = self.options["prompt_text"]
# Prepare text