Files
voicebox/backend/routes/audio.py
T
Jamie Pine 3d4d0a9335 fix(audio): serve real Content-Type so imports decode in WaveSurfer
/audio/{id} and /audio/version/{id} hardcoded media_type="audio/wav" on
the FileResponse. That was a no-op when every generation came out of
TTS (everything on disk was a .wav anyway), but imported audio keeps
its source format — .mp3 / .m4a / .ogg — and the WaveSurfer MediaElement
backend uses an <audio> tag that checks Content-Type before letting the
clip play, so an MP3 announced as audio/wav silently failed to load.

Both endpoints now derive the type via mimetypes.guess_type and fall
back to audio/wav for unknown suffixes. Download filenames also keep
the real extension instead of always saying ".wav".
2026-04-25 02:00:54 -07:00

83 lines
2.8 KiB
Python

"""Audio file serving endpoints."""
import mimetypes
from pathlib import Path
from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import FileResponse
from sqlalchemy.orm import Session
from .. import config, models
from ..services import history
from ..database import get_db
router = APIRouter()
def _audio_media_type(path: Path) -> str:
"""Derive the Content-Type from the file extension.
Imported audio retains its source format (.mp3, .m4a, .ogg, …) so a
blanket ``audio/wav`` would mislead strict clients trying to decode
via the response header instead of sniffing the bytes."""
guessed, _ = mimetypes.guess_type(path.name)
return guessed or "audio/wav"
@router.get("/audio/version/{version_id}")
async def get_version_audio(version_id: str, db: Session = Depends(get_db)):
"""Serve audio for a specific version."""
from ..services import versions as versions_mod
version = versions_mod.get_version(version_id, db)
if not version:
raise HTTPException(status_code=404, detail="Version not found")
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(
audio_path,
media_type=_audio_media_type(audio_path),
filename=f"generation_{version.generation_id}_{version.label}{audio_path.suffix}",
)
@router.get("/audio/{generation_id}")
async def get_audio(generation_id: str, db: Session = Depends(get_db)):
"""Serve generated audio file (serves the default version)."""
generation = await history.get_generation(generation_id, db)
if not generation:
raise HTTPException(status_code=404, detail="Generation not found")
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(
audio_path,
media_type=_audio_media_type(audio_path),
filename=f"generation_{generation_id}{audio_path.suffix}",
)
@router.get("/samples/{sample_id}")
async def get_sample_audio(sample_id: str, db: Session = Depends(get_db)):
"""Serve profile sample audio file."""
from ..database import ProfileSample as DBProfileSample
sample = db.query(DBProfileSample).filter_by(id=sample_id).first()
if not sample:
raise HTTPException(status_code=404, detail="Sample not found")
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(
audio_path,
media_type="audio/wav",
filename=f"sample_{sample_id}.wav",
)