Transcribe audio
Create timed captions with Whisper. Your audio stays on this device.
The workbench couldn’t start. Reload the page to refresh its files, or try a current version of Chrome or Edge.
Audio files 0
Drop audio files here
Transcription settings
Ready to transcribe
Whisper Small downloads on first use, about 255 MB.
Captions
No captions yet
Add an audio file and select Transcribe.
SRT Studio for Windows
Transcribe larger batches locally. NVIDIA CUDA can substantially speed up transcription on a compatible GPU. CPU mode is also available.
- Whisper Small has an estimated 500 MB model download and needs about 2 GB of GPU memory.
- Whisper Large v3 Turbo has an estimated 1.6 GB model download and needs about 6 GB of GPU memory. Allow extra headroom for other apps.
The ZIP contains the app. Model weights download separately during setup and can be cached for offline use.
Download for Windows