Skip to content

The open-source AI voice studio. Clone, dictate, create.

fix: store media paths relative to data dir

James Pineb108bb1cb183
diff --git a/backend/config.py b/backend/config.py
index ecfc3920..959731c6 100644
--- a/backend/config.py
+++ b/backend/config.py
@@ -22,6 +22,21 @@ if _custom_models_dir:
_data_dir = Path("data").resolve()
+def _path_relative_to_any_data_dir(path: Path) -> Path | None:
+ """Extract the path within a data dir from an absolute or relative path."""
+ parts = path.parts
+ for idx, part in enumerate(parts):
+ if part != "data":
+ continue
+
+ tail = parts[idx + 1 :]
+ if tail:
+ return Path(*tail)
+ return Path()
+
+ return None
+
+
def set_data_dir(path: str | Path):
"""
Set the data directory path.
@@ -45,6 +60,38 @@ def get_data_dir() -> Path:
return _data_dir
+def to_storage_path(path: str | Path) -> str:
+ """Convert a filesystem path to a DB-safe path relative to the data dir."""
+ resolved_path = Path(path).resolve()
+
+ relative_to_any_data_dir = _path_relative_to_any_data_dir(resolved_path)
+ if relative_to_any_data_dir is not None:
+ return str(relative_to_any_data_dir)
+
+ try:
+ return str(resolved_path.relative_to(_data_dir))
+ except ValueError:
+ return str(resolved_path)
+
+
+def resolve_storage_path(path: str | Path | None) -> Path | None:
+ """Resolve a DB-stored path against the configured data dir."""
+ if path is None:
+ return None
+
+ stored_path = Path(path)
+ if stored_path.is_absolute():
+ rebased_path = _path_relative_to_any_data_dir(stored_path)
+ if rebased_path is not None:
+ candidate = (_data_dir / rebased_path).resolve()
+ if candidate.exists() or not stored_path.exists():
+ return candidate
+
+ return stored_path
+
+ return (_data_dir / stored_path).resolve()
+
+
def get_db_path() -> Path:
"""Get database file path."""
return _data_dir / "voicebox.db"
diff --git a/backend/database/migrations.py b/backend/database/migrations.py
index 6256d92b..2bdd9282 100644
--- a/backend/database/migrations.py
+++ b/backend/database/migrations.py
@@ -34,7 +34,7 @@ def run_migrations(engine) -> None:
_migrate_generations(engine, inspector, tables)
_migrate_effect_presets(engine, inspector, tables)
_migrate_generation_versions(engine, inspector, tables)
- _resolve_relative_paths(engine, tables)
+ _normalize_storage_paths(engine, tables)
# -- helpers ---------------------------------------------------------------
@@ -182,24 +182,11 @@ def _migrate_generation_versions(engine, inspector, tables: set[str]) -> None:
_add_column(engine, "generation_versions", "source_version_id VARCHAR", "source_version_id")
-def _resolve_relative_paths(engine, tables: set[str]) -> None:
- """Resolve any relative file paths in the database to absolute paths.
-
- Earlier versions stored paths relative to CWD (e.g. "data/generations/abc.wav").
- These break when the production binary's CWD differs from the data directory.
- This migration converts them to absolute paths using the configured data dir.
- Idempotent: absolute paths are left untouched.
-
- Strategy: paths like "data/generations/abc.wav" are rebased onto the
- configured data directory. If the path starts with "data/", strip that
- prefix and prepend get_data_dir(). Otherwise, join the relative path
- directly under get_data_dir().
- directly under get_data_dir(). If the rebased path still does not exist,
- fall back to resolving relative to CWD.
- """
+def _normalize_storage_paths(engine, tables: set[str]) -> None:
+ """Normalize stored file paths to be relative to the configured data dir."""
from pathlib import Path
- from ..config import get_data_dir
+ from ..config import get_data_dir, to_storage_path, resolve_storage_path
data_dir = get_data_dir()
@@ -222,21 +209,18 @@ def _resolve_relative_paths(engine, tables: set[str]) -> None:
if not path_val:
continue
p = Path(path_val)
- if p.is_absolute():
+ resolved = resolve_storage_path(p)
+ if resolved is None:
continue
- parts = p.parts
- if parts and parts[0] == "data":
- rebased = (data_dir / Path(*parts[1:])).resolve()
- else:
- rebased = (data_dir / p).resolve()
-
- resolved = rebased if rebased.exists() else p.resolve()
- if resolved.exists():
+
+ normalized = to_storage_path(resolved)
+
+ if normalized != path_val:
conn.execute(
text(f"UPDATE {table} SET {column} = :path WHERE id = :id"),
- {"path": str(resolved), "id": row_id},
+ {"path": normalized, "id": row_id},
)
total_fixed += 1
if total_fixed > 0:
conn.commit()
- logger.info("Resolved %d relative file paths to absolute", total_fixed)
+ logger.info("Normalized %d stored file paths", total_fixed)
diff --git a/backend/database/seed.py b/backend/database/seed.py
index b62edc22..b09e0b8f 100644
--- a/backend/database/seed.py
+++ b/backend/database/seed.py
@@ -3,7 +3,8 @@
import json
import logging
import uuid
-from pathlib import Path
+
+from .. import config
logger = logging.getLogger(__name__)
@@ -25,7 +26,8 @@ def backfill_generation_versions(SessionLocal, Generation, GenerationVersion) ->
for gen in generations:
if gen.id in existing_version_gen_ids:
continue
- if not Path(gen.audio_path).exists():
+ resolved_audio_path = config.resolve_storage_path(gen.audio_path)
+ if resolved_audio_path is None or not resolved_audio_path.exists():
continue
version = GenerationVersion(
id=str(uuid.uuid4()),
diff --git a/backend/routes/audio.py b/backend/routes/audio.py
index 682d7aae..f80a44d5 100644
--- a/backend/routes/audio.py
+++ b/backend/routes/audio.py
@@ -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(
diff --git a/backend/routes/effects.py b/backend/routes/effects.py
index 8139176d..52bbc8fd 100644
--- a/backend/routes/effects.py
+++ b/backend/routes/effects.py
@@ -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,
diff --git a/backend/routes/history.py b/backend/routes/history.py
index 5435e299..f8233e3c 100644
--- a/backend/routes/history.py
+++ b/backend/routes/history.py
@@ -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()
diff --git a/backend/routes/profiles.py b/backend/routes/profiles.py
index d65a1138..7bc075c5 100644
--- a/backend/routes/profiles.py
+++ b/backend/routes/profiles.py
@@ -10,7 +10,7 @@ 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
@@ -258,8 +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)
diff --git a/backend/services/export_import.py b/backend/services/export_import.py
index 93252f50..514eaacd 100644
--- a/backend/services/export_import.py
+++ b/backend/services/export_import.py
@@ -73,8 +73,8 @@ def export_profile_to_zip(profile_id: str, db: Session) -> bytes:
# Check if profile has avatar
has_avatar = False
if profile.avatar_path:
- avatar_path = Path(profile.avatar_path)
- if avatar_path.exists():
+ avatar_path = config.resolve_storage_path(profile.avatar_path)
+ if avatar_path is not None and avatar_path.exists():
has_avatar = True
# Add avatar to ZIP root with original extension
avatar_ext = avatar_path.suffix
@@ -98,7 +98,9 @@ def export_profile_to_zip(profile_id: str, db: Session) -> bytes:
for sample in samples:
# Get filename from audio_path (should be {sample_id}.wav)
- audio_path = Path(sample.audio_path)
+ audio_path = config.resolve_storage_path(sample.audio_path)
+ if audio_path is None:
+ raise ValueError(f"Audio file not found: {sample.audio_path}")
filename = audio_path.name
# Read audio file
@@ -279,7 +281,7 @@ def export_generation_to_zip(generation_id: str, db: Session) -> bytes:
# Build version manifest entries
version_entries = []
for v in versions:
- v_path = Path(v.audio_path)
+ v_path = config.resolve_storage_path(v.audio_path)
effects_chain = None
if v.effects_chain:
effects_chain = json.loads(v.effects_chain)
@@ -314,14 +316,14 @@ def export_generation_to_zip(generation_id: str, db: Session) -> bytes:
# Add all version audio files
for v in versions:
- v_path = Path(v.audio_path)
- if v_path.exists():
+ v_path = config.resolve_storage_path(v.audio_path)
+ if v_path is not None and v_path.exists():
zip_file.write(v_path, f"audio/{v_path.name}")
# Fallback: if no versions exist, include the generation's main audio
if not versions:
- audio_path = Path(generation.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(generation.audio_path)
+ if audio_path is not None and audio_path.exists():
zip_file.write(audio_path, f"audio/{audio_path.name}")
zip_buffer.seek(0)
@@ -426,7 +428,7 @@ async def import_generation_from_zip(file_bytes: bytes, db: Session) -> dict:
profile_id=profile_id,
text=generation_data["text"],
language=generation_data["language"],
- audio_path=str(audio_dest),
+ audio_path=config.to_storage_path(audio_dest),
duration=generation_data["duration"],
seed=generation_data.get("seed"),
instruct=generation_data.get("instruct"),
diff --git a/backend/services/generation.py b/backend/services/generation.py
index d8d5214d..a70e633e 100644
--- a/backend/services/generation.py
+++ b/backend/services/generation.py
@@ -163,7 +163,7 @@ def _save_generate(
versions_mod.create_version(
generation_id=generation_id,
label="original",
- audio_path=str(clean_audio_path),
+ audio_path=config.to_storage_path(clean_audio_path),
db=db,
effects_chain=None,
is_default=not has_effects,
@@ -174,6 +174,8 @@ def _save_generate(
if has_effects:
from ..utils.effects import apply_effects, validate_effects_chain
+ assert effects_chain is not None
+
error_msg = validate_effects_chain(effects_chain)
if error_msg:
import logging
@@ -189,13 +191,13 @@ def _save_generate(
versions_mod.create_version(
generation_id=generation_id,
label="version-2",
- audio_path=str(processed_path),
+ audio_path=config.to_storage_path(processed_path),
db=db,
effects_chain=effects_chain,
is_default=True,
)
- return final_audio_path
+ return config.to_storage_path(final_audio_path)
def _save_retry(
@@ -211,7 +213,7 @@ def _save_retry(
"""
audio_path = config.get_generations_dir() / f"{generation_id}.wav"
save_audio(audio, str(audio_path), sample_rate)
- return str(audio_path)
+ return config.to_storage_path(audio_path)
def _save_regenerate(
@@ -244,10 +246,10 @@ def _save_regenerate(
versions_mod.create_version(
generation_id=generation_id,
label=label,
- audio_path=str(audio_path),
+ audio_path=config.to_storage_path(audio_path),
db=db,
effects_chain=None,
is_default=True,
)
- return str(audio_path)
+ return config.to_storage_path(audio_path)
diff --git a/backend/services/history.py b/backend/services/history.py
index 8f45d48f..473c4b37 100644
--- a/backend/services/history.py
+++ b/backend/services/history.py
@@ -253,8 +253,8 @@ async def delete_generation(
# Delete main audio file (if not already removed by version cleanup)
if generation.audio_path:
- audio_path = Path(generation.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(generation.audio_path)
+ if audio_path is not None and audio_path.exists():
audio_path.unlink()
# Delete from database
@@ -283,8 +283,8 @@ async def delete_generations_by_profile(
count = 0
for generation in generations:
# Delete audio file
- audio_path = Path(generation.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(generation.audio_path)
+ if audio_path is not None and audio_path.exists():
audio_path.unlink()
# Delete from database
diff --git a/backend/services/profiles.py b/backend/services/profiles.py
index cd418aab..78839504 100644
--- a/backend/services/profiles.py
+++ b/backend/services/profiles.py
@@ -236,7 +236,7 @@ async def add_profile_sample(
db_sample = DBProfileSample(
id=sample_id,
profile_id=profile_id,
- audio_path=str(dest_path),
+ audio_path=config.to_storage_path(dest_path),
reference_text=reference_text,
)
@@ -441,8 +441,8 @@ async def delete_profile_sample(
# Store profile_id before deleting
profile_id = sample.profile_id
- audio_path = Path(sample.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(sample.audio_path)
+ if audio_path is not None and audio_path.exists():
audio_path.unlink()
db.delete(sample)
@@ -556,14 +556,22 @@ async def create_voice_prompt_for_profile(
if len(samples) == 1:
sample = samples[0]
+ sample_audio_path = config.resolve_storage_path(sample.audio_path)
+ if sample_audio_path is None:
+ raise ValueError(f"Sample audio not found for profile {profile_id}")
voice_prompt, _ = await tts_model.create_voice_prompt(
- sample.audio_path,
+ str(sample_audio_path),
sample.reference_text,
use_cache=use_cache,
)
return voice_prompt
- audio_paths = [s.audio_path for s in samples]
+ audio_paths = []
+ for sample in samples:
+ sample_audio_path = config.resolve_storage_path(sample.audio_path)
+ if sample_audio_path is None:
+ raise ValueError(f"Sample audio not found for profile {profile_id}")
+ audio_paths.append(str(sample_audio_path))
reference_texts = [s.reference_text for s in samples]
combined_audio, combined_text = await tts_model.combine_voice_prompts(
@@ -617,8 +625,8 @@ async def upload_avatar(
raise ValueError(error_msg)
if profile.avatar_path:
- old_avatar = Path(profile.avatar_path)
- if old_avatar.exists():
+ old_avatar = config.resolve_storage_path(profile.avatar_path)
+ if old_avatar is not None and old_avatar.exists():
old_avatar.unlink()
# Determine file extension from uploaded file
@@ -639,7 +647,7 @@ async def upload_avatar(
process_avatar(image_path, str(output_path))
- profile.avatar_path = str(output_path)
+ profile.avatar_path = config.to_storage_path(output_path)
profile.updated_at = datetime.utcnow()
db.commit()
@@ -666,8 +674,8 @@ async def delete_avatar(
if not profile or not profile.avatar_path:
return False
- avatar_path = Path(profile.avatar_path)
- if avatar_path.exists():
+ avatar_path = config.resolve_storage_path(profile.avatar_path)
+ if avatar_path is not None and avatar_path.exists():
avatar_path.unlink()
profile.avatar_path = None
diff --git a/backend/services/stories.py b/backend/services/stories.py
index ac8e22bd..611ab29d 100644
--- a/backend/services/stories.py
+++ b/backend/services/stories.py
@@ -10,6 +10,7 @@ from pathlib import Path
from sqlalchemy.orm import Session
from sqlalchemy import func
+from .. import config
from ..models import (
StoryCreate,
StoryResponse,
@@ -826,8 +827,8 @@ async def export_story_audio(
if version:
resolved_audio_path = version.audio_path
- audio_path = Path(resolved_audio_path)
- if not audio_path.exists():
+ audio_path = config.resolve_storage_path(resolved_audio_path)
+ if audio_path is None or not audio_path.exists():
continue
try:
diff --git a/backend/services/versions.py b/backend/services/versions.py
index 1743a25c..cbeb4b8b 100644
--- a/backend/services/versions.py
+++ b/backend/services/versions.py
@@ -158,8 +158,8 @@ def delete_version(version_id: str, db: Session) -> bool:
gen_id = version.generation_id
# Delete audio file
- audio_path = Path(version.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(version.audio_path)
+ if audio_path is not None and audio_path.exists():
audio_path.unlink()
db.delete(version)
@@ -193,8 +193,8 @@ def delete_versions_for_generation(generation_id: str, db: Session) -> int:
)
count = 0
for v in versions:
- audio_path = Path(v.audio_path)
- if audio_path.exists():
+ audio_path = config.resolve_storage_path(v.audio_path)
+ if audio_path is not None and audio_path.exists():
audio_path.unlink()
db.delete(v)
count += 1