Self-hosted speech-to-text via faster-whisper. Streams progress over SSE.
Version: 1.0.0
Drop a video or audio file below to transcribe it live.
No file selected.
Returns text/event-stream. JSON body with gcs_url or multipart upload at POST /transcribe/upload.
{
"gcs_url": "https://storage.googleapis.com/bucket/video.mp4",
"quality": "fast"
}
| quality | model | RAM / job |
|---|---|---|
| fast | small int8 | ~2.5 GB |
| balanced | medium int8 | ~4 GB |
| best | large-v3-turbo int8 | ~7 GB |
event: started event: segment event: done event: error
Optional — currently open (no AUTH_TOKEN set).
JSON status, loaded models, active jobs, memory stats.