33cca5f552
CutScript is a local-first, Descript-like video editor where you edit video by editing text. Delete a word from the transcript and it's cut from the video. Features: - Word-level transcription with WhisperX - Text-based video editing with undo/redo - AI filler word removal (Ollama/OpenAI/Claude) - AI clip creation for shorts - Waveform timeline with virtualized transcript - FFmpeg stream-copy (fast) and re-encode (4K) export - Caption burn-in and sidecar SRT generation - Studio Sound audio enhancement (DeepFilterNet) - Keyboard shortcuts (J/K/L, Space, Delete, Ctrl+Z/S/E) - Encrypted API key storage - Project save/load (.aive files) Architecture: - Electron + React + Tailwind (frontend) - FastAPI + Python (backend) - WhisperX for transcription - FFmpeg for video processing - Multi-provider AI support Performance optimizations: - RAF-throttled time updates - Zustand selectors for granular subscriptions - Dual-canvas waveform rendering - Virtualized transcript with react-virtuoso Built on top of DataAnts-AI/VideoTranscriber, completely rewritten as a desktop application. License: MIT
54 lines
1.5 KiB
Python
54 lines
1.5 KiB
Python
"""Transcription endpoint using WhisperX."""
|
|
|
|
import logging
|
|
from typing import Optional
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel
|
|
|
|
from services.transcription import transcribe_audio
|
|
from services.diarization import diarize_and_label
|
|
|
|
logger = logging.getLogger(__name__)
|
|
router = APIRouter()
|
|
|
|
|
|
class TranscribeRequest(BaseModel):
|
|
file_path: str
|
|
model: str = "base"
|
|
language: Optional[str] = None
|
|
use_gpu: bool = True
|
|
use_cache: bool = True
|
|
diarize: bool = False
|
|
hf_token: Optional[str] = None
|
|
num_speakers: Optional[int] = None
|
|
|
|
|
|
@router.post("/transcribe")
|
|
async def transcribe(req: TranscribeRequest):
|
|
try:
|
|
result = transcribe_audio(
|
|
file_path=req.file_path,
|
|
model_name=req.model,
|
|
use_gpu=req.use_gpu,
|
|
use_cache=req.use_cache,
|
|
language=req.language,
|
|
)
|
|
|
|
if req.diarize and req.hf_token:
|
|
result = diarize_and_label(
|
|
transcription_result=result,
|
|
audio_path=req.file_path,
|
|
hf_token=req.hf_token,
|
|
num_speakers=req.num_speakers,
|
|
use_gpu=req.use_gpu,
|
|
)
|
|
|
|
return result
|
|
|
|
except FileNotFoundError:
|
|
raise HTTPException(status_code=404, detail=f"File not found: {req.file_path}")
|
|
except Exception as e:
|
|
logger.error(f"Transcription failed: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=str(e))
|