mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
James Pine
3584283d84
Add Kokoro-82M as a new TTS engine — 82M params, CPU realtime, 8 languages, Apache 2.0. Unlike cloning engines, Kokoro uses pre-built voice styles, which required a new profile type system to support non-cloning engines cleanly. Kokoro engine: - New kokoro_backend.py implementing TTSBackend protocol - 50 built-in voices across en/es/fr/hi/it/pt/ja/zh - KPipeline API with language-aware G2P routing via misaki - PyInstaller bundling for misaki, language_tags, espeakng_loader, en_core_web_sm Voice profile type system: - New voice_type column: 'cloned' | 'preset' | 'designed' (future) - Preset profiles store engine + voice ID instead of audio samples - default_engine field on profiles — auto-selects engine on profile pick - Create Voice dialog: toggle between 'Clone from audio' and 'Built-in voice' - Edit dialog shows preset voice info instead of sample list for preset profiles - Engine selector locks to preset engine when preset profile is selected - Profile grid filters by engine — shows Kokoro voices when Kokoro selected - Custom empty state when no preset profiles exist for selected engine Bug fixes: - Fix relative audio paths in DB causing 404s in production builds - config.set_data_dir() now resolves to absolute paths - Startup migration converts existing relative paths to absolute Also updates PROJECT_STATUS.md and tts-engines.mdx developer guide.
170 lines
6.3 KiB
Python
170 lines
6.3 KiB
Python
"""ORM model definitions for the voicebox SQLite database."""
|
|
|
|
from datetime import datetime
|
|
import uuid
|
|
|
|
from sqlalchemy import Column, String, Integer, Float, DateTime, Text, ForeignKey, Boolean
|
|
from sqlalchemy.ext.declarative import declarative_base
|
|
|
|
Base = declarative_base()
|
|
|
|
|
|
class VoiceProfile(Base):
|
|
"""Voice profile.
|
|
|
|
voice_type discriminates three flavours:
|
|
- "cloned" — traditional reference-audio profiles (all cloning engines)
|
|
- "preset" — engine-specific pre-built voice (e.g. Kokoro voices)
|
|
- "designed" — text-described voice (e.g. Qwen CustomVoice, future)
|
|
"""
|
|
|
|
__tablename__ = "profiles"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String, unique=True, nullable=False)
|
|
description = Column(Text)
|
|
language = Column(String, default="en")
|
|
avatar_path = Column(String, nullable=True)
|
|
effects_chain = Column(Text, nullable=True)
|
|
|
|
# Voice type system — added v0.3.x
|
|
voice_type = Column(String, default="cloned") # "cloned" | "preset" | "designed"
|
|
preset_engine = Column(String, nullable=True) # e.g. "kokoro" — only for preset
|
|
preset_voice_id = Column(String, nullable=True) # e.g. "am_adam" — only for preset
|
|
design_prompt = Column(Text, nullable=True) # text description — only for designed
|
|
default_engine = Column(String, nullable=True) # auto-selected engine, locked for preset
|
|
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
|
|
|
|
|
|
class ProfileSample(Base):
|
|
"""Audio sample attached to a voice profile."""
|
|
|
|
__tablename__ = "profile_samples"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
profile_id = Column(String, ForeignKey("profiles.id"), nullable=False)
|
|
audio_path = Column(String, nullable=False)
|
|
reference_text = Column(Text, nullable=False)
|
|
|
|
|
|
class Generation(Base):
|
|
"""A single TTS generation."""
|
|
|
|
__tablename__ = "generations"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
profile_id = Column(String, ForeignKey("profiles.id"), nullable=False)
|
|
text = Column(Text, nullable=False)
|
|
language = Column(String, default="en")
|
|
audio_path = Column(String, nullable=True)
|
|
duration = Column(Float, nullable=True)
|
|
seed = Column(Integer)
|
|
instruct = Column(Text)
|
|
engine = Column(String, default="qwen")
|
|
model_size = Column(String, nullable=True)
|
|
status = Column(String, default="completed")
|
|
error = Column(Text, nullable=True)
|
|
is_favorited = Column(Boolean, default=False)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
|
|
|
|
class Story(Base):
|
|
"""A story that sequences multiple generations."""
|
|
|
|
__tablename__ = "stories"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String, nullable=False)
|
|
description = Column(Text)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
|
|
|
|
|
|
class StoryItem(Base):
|
|
"""Links a generation to a story at a specific timecode."""
|
|
|
|
__tablename__ = "story_items"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
story_id = Column(String, ForeignKey("stories.id"), nullable=False)
|
|
generation_id = Column(String, ForeignKey("generations.id"), nullable=False)
|
|
version_id = Column(String, ForeignKey("generation_versions.id"), nullable=True)
|
|
start_time_ms = Column(Integer, nullable=False, default=0)
|
|
track = Column(Integer, nullable=False, default=0)
|
|
trim_start_ms = Column(Integer, nullable=False, default=0)
|
|
trim_end_ms = Column(Integer, nullable=False, default=0)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
|
|
|
|
class Project(Base):
|
|
"""Audio studio project (JSON blob)."""
|
|
|
|
__tablename__ = "projects"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String, nullable=False)
|
|
data = Column(Text)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
|
|
|
|
|
|
class GenerationVersion(Base):
|
|
"""A version of a generation's audio (original, processed, alternate takes)."""
|
|
|
|
__tablename__ = "generation_versions"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
generation_id = Column(String, ForeignKey("generations.id"), nullable=False)
|
|
label = Column(String, nullable=False)
|
|
audio_path = Column(String, nullable=False)
|
|
effects_chain = Column(Text, nullable=True)
|
|
source_version_id = Column(String, ForeignKey("generation_versions.id"), nullable=True)
|
|
is_default = Column(Boolean, default=False)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
|
|
|
|
class EffectPreset(Base):
|
|
"""Saved effect chain preset."""
|
|
|
|
__tablename__ = "effect_presets"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String, unique=True, nullable=False)
|
|
description = Column(Text, nullable=True)
|
|
effects_chain = Column(Text, nullable=False)
|
|
is_builtin = Column(Boolean, default=False)
|
|
sort_order = Column(Integer, default=100)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
|
|
|
|
class AudioChannel(Base):
|
|
"""Audio output channel (bus)."""
|
|
|
|
__tablename__ = "audio_channels"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String, nullable=False)
|
|
is_default = Column(Boolean, default=False)
|
|
created_at = Column(DateTime, default=datetime.utcnow)
|
|
|
|
|
|
class ChannelDeviceMapping(Base):
|
|
"""Mapping between a channel and an OS audio device."""
|
|
|
|
__tablename__ = "channel_device_mappings"
|
|
|
|
id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
channel_id = Column(String, ForeignKey("audio_channels.id"), nullable=False)
|
|
device_id = Column(String, nullable=False)
|
|
|
|
|
|
class ProfileChannelMapping(Base):
|
|
"""Many-to-many mapping between voice profiles and audio channels."""
|
|
|
|
__tablename__ = "profile_channel_mappings"
|
|
|
|
profile_id = Column(String, ForeignKey("profiles.id"), primary_key=True)
|
|
channel_id = Column(String, ForeignKey("audio_channels.id"), primary_key=True)
|