mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-29 15:15:27 -07:00
Merge pull request #319 from jamiepine/fix/startup-and-server-switch
fix: GUI startup with external server + data refresh on server switch
This commit is contained in:
@@ -1,12 +1,10 @@
|
||||
"""Audio file serving endpoints."""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi.responses import FileResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from .. import models
|
||||
from .. import config, models
|
||||
from ..services import history
|
||||
from ..database import get_db
|
||||
|
||||
@@ -22,8 +20,8 @@ async def get_version_audio(version_id: str, db: Session = Depends(get_db)):
|
||||
if not version:
|
||||
raise HTTPException(status_code=404, detail="Version not found")
|
||||
|
||||
audio_path = Path(version.audio_path)
|
||||
if not audio_path.exists():
|
||||
audio_path = config.resolve_storage_path(version.audio_path)
|
||||
if audio_path is None or not audio_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
return FileResponse(
|
||||
@@ -40,8 +38,8 @@ async def get_audio(generation_id: str, db: Session = Depends(get_db)):
|
||||
if not generation:
|
||||
raise HTTPException(status_code=404, detail="Generation not found")
|
||||
|
||||
audio_path = Path(generation.audio_path)
|
||||
if not audio_path.exists():
|
||||
audio_path = config.resolve_storage_path(generation.audio_path)
|
||||
if audio_path is None or not audio_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
return FileResponse(
|
||||
@@ -60,8 +58,8 @@ async def get_sample_audio(sample_id: str, db: Session = Depends(get_db)):
|
||||
if not sample:
|
||||
raise HTTPException(status_code=404, detail="Sample not found")
|
||||
|
||||
audio_path = Path(sample.audio_path)
|
||||
if not audio_path.exists():
|
||||
audio_path = config.resolve_storage_path(sample.audio_path)
|
||||
if audio_path is None or not audio_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
return FileResponse(
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
import asyncio
|
||||
import io
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi.responses import StreamingResponse
|
||||
@@ -41,10 +40,11 @@ async def preview_effects(
|
||||
all_versions = versions_mod.list_versions(generation_id, db)
|
||||
clean_version = next((v for v in all_versions if v.effects_chain is None), None)
|
||||
source_path = clean_version.audio_path if clean_version else gen.audio_path
|
||||
if not source_path or not Path(source_path).exists():
|
||||
resolved_source_path = config.resolve_storage_path(source_path)
|
||||
if resolved_source_path is None or not resolved_source_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Source audio file not found")
|
||||
|
||||
audio, sample_rate = await asyncio.to_thread(load_audio, source_path)
|
||||
audio, sample_rate = await asyncio.to_thread(load_audio, str(resolved_source_path))
|
||||
processed = await asyncio.to_thread(apply_effects, audio, sample_rate, chain_dicts)
|
||||
|
||||
import soundfile as sf
|
||||
@@ -193,10 +193,11 @@ async def apply_effects_to_generation(
|
||||
source_path = clean_version.audio_path
|
||||
source_version_id = clean_version.id
|
||||
|
||||
if not source_path or not Path(source_path).exists():
|
||||
resolved_source_path = config.resolve_storage_path(source_path)
|
||||
if resolved_source_path is None or not resolved_source_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Source audio file not found")
|
||||
|
||||
audio, sample_rate = await asyncio.to_thread(load_audio, source_path)
|
||||
audio, sample_rate = await asyncio.to_thread(load_audio, str(resolved_source_path))
|
||||
processed_audio = await asyncio.to_thread(apply_effects, audio, sample_rate, chain_dicts)
|
||||
|
||||
version_id = str(uuid.uuid4())
|
||||
@@ -208,7 +209,7 @@ async def apply_effects_to_generation(
|
||||
version = versions_mod.create_version(
|
||||
generation_id=generation_id,
|
||||
label=label,
|
||||
audio_path=str(processed_path),
|
||||
audio_path=config.to_storage_path(processed_path),
|
||||
db=db,
|
||||
effects_chain=chain_dicts,
|
||||
is_default=data.set_as_default,
|
||||
|
||||
@@ -20,6 +20,10 @@ from ..utils.tasks import get_task_manager
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _resolve_generation_engine(data: models.GenerationRequest, profile) -> str:
|
||||
return data.engine or getattr(profile, "default_engine", None) or getattr(profile, "preset_engine", None) or "qwen"
|
||||
|
||||
|
||||
@router.post("/generate", response_model=models.GenerationResponse)
|
||||
async def generate_speech(
|
||||
data: models.GenerationRequest,
|
||||
@@ -35,7 +39,12 @@ async def generate_speech(
|
||||
|
||||
from ..backends import engine_has_model_sizes
|
||||
|
||||
engine = data.engine or "qwen"
|
||||
engine = _resolve_generation_engine(data, profile)
|
||||
try:
|
||||
profiles.validate_profile_engine(profile, engine)
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
|
||||
model_size = (data.model_size or "1.7B") if engine_has_model_sizes(engine) else None
|
||||
|
||||
generation = await history.create_generation(
|
||||
@@ -230,15 +239,11 @@ async def stream_speech(
|
||||
if not profile:
|
||||
raise HTTPException(status_code=404, detail="Profile not found")
|
||||
|
||||
# Mirror the regular /generate endpoint behavior more closely:
|
||||
# if the caller doesn't specify an engine, prefer the profile's default
|
||||
# engine (or preset engine) before falling back to qwen.
|
||||
engine = (
|
||||
data.engine
|
||||
or getattr(profile, "default_engine", None)
|
||||
or getattr(profile, "preset_engine", None)
|
||||
or "qwen"
|
||||
)
|
||||
engine = _resolve_generation_engine(data, profile)
|
||||
try:
|
||||
profiles.validate_profile_engine(profile, engine)
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
tts_model = get_tts_backend_for_engine(engine)
|
||||
model_size = data.model_size or "1.7B"
|
||||
|
||||
|
||||
@@ -1,13 +1,12 @@
|
||||
"""Generation history endpoints."""
|
||||
|
||||
import io
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile
|
||||
from fastapi.responses import FileResponse, StreamingResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from .. import models
|
||||
from .. import config, models
|
||||
from ..services import export_import, history
|
||||
from ..app import safe_content_disposition
|
||||
from ..database import Generation as DBGeneration, VoiceProfile as DBVoiceProfile, get_db
|
||||
@@ -162,8 +161,8 @@ async def export_generation_audio(
|
||||
if not generation.audio_path:
|
||||
raise HTTPException(status_code=404, detail="Generation has no audio file")
|
||||
|
||||
audio_path = Path(generation.audio_path)
|
||||
if not audio_path.is_file():
|
||||
audio_path = config.resolve_storage_path(generation.audio_path)
|
||||
if audio_path is None or not audio_path.is_file():
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
safe_text = "".join(c for c in generation.text[:30] if c.isalnum() or c in (" ", "-", "_")).strip()
|
||||
|
||||
+18
-73
@@ -4,15 +4,13 @@ import io
|
||||
import json as _json
|
||||
import logging
|
||||
import tempfile
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile
|
||||
from fastapi.responses import FileResponse, StreamingResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from .. import models
|
||||
from .. import config, models
|
||||
from ..app import safe_content_disposition
|
||||
from ..database import VoiceProfile as DBVoiceProfile, get_db
|
||||
from ..services import channels, export_import, profiles
|
||||
@@ -90,76 +88,23 @@ async def list_preset_voices(engine: str):
|
||||
for vid, name, gender, lang in KOKORO_VOICES
|
||||
],
|
||||
}
|
||||
if engine == "qwen_custom_voice":
|
||||
from ..backends.qwen_custom_voice_backend import QWEN_CUSTOM_VOICES
|
||||
|
||||
return {
|
||||
"engine": engine,
|
||||
"voices": [
|
||||
{
|
||||
"voice_id": speaker_id,
|
||||
"name": display_name,
|
||||
"gender": gender,
|
||||
"language": lang,
|
||||
}
|
||||
for speaker_id, display_name, gender, lang, _desc in QWEN_CUSTOM_VOICES
|
||||
],
|
||||
}
|
||||
return {"engine": engine, "voices": []}
|
||||
|
||||
|
||||
@router.post("/profiles/presets/{engine}/seed")
|
||||
async def seed_preset_profiles_route(
|
||||
engine: str,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""Seed preset voice profiles for an engine.
|
||||
|
||||
Creates profiles for all available preset voices that don't already exist.
|
||||
Returns the count of newly created profiles.
|
||||
"""
|
||||
if engine != "kokoro":
|
||||
raise HTTPException(status_code=400, detail=f"No presets available for engine: {engine}")
|
||||
|
||||
try:
|
||||
from ..backends.kokoro_backend import KOKORO_VOICES
|
||||
|
||||
created = 0
|
||||
for voice_id, display_name, gender, lang in KOKORO_VOICES:
|
||||
profile_name = display_name
|
||||
|
||||
# Disambiguate duplicate display names across languages
|
||||
# (e.g. "Alpha" exists in Hindi and Japanese, "Dora" in Spanish and Portuguese)
|
||||
dupes = [v for v in KOKORO_VOICES if v[1] == display_name]
|
||||
if len(dupes) > 1:
|
||||
lang_labels = {"en": "English", "es": "Spanish", "fr": "French", "hi": "Hindi",
|
||||
"it": "Italian", "pt": "Portuguese", "ja": "Japanese", "zh": "Chinese"}
|
||||
profile_name = f"{display_name} {lang_labels.get(lang, lang)}"
|
||||
|
||||
# Skip if preset already exists
|
||||
existing = (
|
||||
db.query(DBVoiceProfile)
|
||||
.filter_by(preset_engine="kokoro", preset_voice_id=voice_id)
|
||||
.first()
|
||||
)
|
||||
if existing:
|
||||
continue
|
||||
|
||||
unique_name = profile_name
|
||||
suffix = 2
|
||||
while db.query(DBVoiceProfile).filter_by(name=unique_name).first():
|
||||
unique_name = f"{profile_name} {suffix}"
|
||||
suffix += 1
|
||||
|
||||
profile = DBVoiceProfile(
|
||||
id=str(uuid.uuid4()),
|
||||
name=unique_name,
|
||||
description=f"Kokoro preset voice — {display_name} ({gender})",
|
||||
language=lang,
|
||||
voice_type="preset",
|
||||
preset_engine="kokoro",
|
||||
preset_voice_id=voice_id,
|
||||
created_at=datetime.utcnow(),
|
||||
updated_at=datetime.utcnow(),
|
||||
)
|
||||
db.add(profile)
|
||||
created += 1
|
||||
|
||||
if created > 0:
|
||||
db.commit()
|
||||
logger.info(f"Seeded {created} Kokoro preset profiles")
|
||||
|
||||
return {"engine": engine, "created": created, "total_available": len(KOKORO_VOICES)}
|
||||
except Exception as e:
|
||||
logger.exception(f"Failed to seed Kokoro profiles: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/profiles/{profile_id}", response_model=models.VoiceProfileResponse)
|
||||
async def get_profile(
|
||||
profile_id: str,
|
||||
@@ -313,8 +258,8 @@ async def get_profile_avatar(
|
||||
if not profile.avatar_path:
|
||||
raise HTTPException(status_code=404, detail="No avatar found for this profile")
|
||||
|
||||
avatar_path = Path(profile.avatar_path)
|
||||
if not avatar_path.exists():
|
||||
avatar_path = config.resolve_storage_path(profile.avatar_path)
|
||||
if avatar_path is None or not avatar_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Avatar file not found")
|
||||
|
||||
return FileResponse(avatar_path)
|
||||
|
||||
Reference in New Issue
Block a user