Media

Speech to Text

Transcribe audio or video to text with local Whisper (faster-whisper). Download a .txt transcript. Privacy-first — no cloud speech API.

Drop your files here

Max 10 MB · media up to 50 MB

or click to browse

About Speech to Text

Transcribe audio and video to text online with local faster-whisper when installed. Privacy-first speech to text on Fah Swe Tools — no OpenAI cloud API, uploads auto-delete within 24 hours.

How it works

  1. Upload an audio or video file (MP3, WAV, M4A, MP4, WebM, etc.).
  2. Optionally pick a language (or leave Auto-detect).
  3. Run transcription and copy or download the .txt. Files auto-delete within 24 hours.

FAQ

Is Whisper required on the server?

Yes — install faster-whisper (pip) and ffmpeg. First run downloads a small model (default: tiny). If the model is missing you get a clear install error instead of a fake transcript.

Is this a cloud API?

No. Transcription runs locally via faster-whisper when installed. Nothing is sent to OpenAI.

What languages work?

Whatever the Whisper model supports — Auto-detect works for most common languages including English and Bangla.