Free Audio Transcription Tool

Upload audio or video. Get text + subtitles back. Powered by Whisper.

Why Forge Transcription vs OpenAI Whisper API & AssemblyAI? → · API docs · All APIs

🎙️

Drop your audio/video file here or click to browse

MP3, WAV, M4A, FLAC, OGG, MP4, WEBM — up to 25MB

Output Format

Transcription

Whisper AI

SRT & VTT

Get subtitles ready for YouTube, Premiere, or any video editor.

Auto Language

Automatic language detection. Works with 90+ languages.

Any Format

MP3, WAV, M4A, FLAC, OGG, MP4, WEBM and more.

No Signup

No account, no API key, no email. Just upload and go.

API Access

Simple POST with file upload. See docs for details.

API Usage

# Transcribe an audio file
curl -X POST -F "file=@recording.mp3" \
  https://forge-node.tail2b516d.ts.net/transcribe

# Get SRT subtitles
curl -X POST -F "file=@video.mp4" -F "output=srt" \
  https://forge-node.tail2b516d.ts.net/transcribe -o subtitles.srt

# Get VTT subtitles
curl -X POST -F "file=@podcast.wav" -F "output=vtt" \
  https://forge-node.tail2b516d.ts.net/transcribe -o subtitles.vtt

Frequently Asked Questions

Is this really free?: Yes. We run Whisper locally. No API costs, so no costs to you. Free forever.
What's the maximum file size?: 25MB. For longer recordings, consider splitting into segments first.
How accurate is it?: Very. Whisper is OpenAI's speech recognition model and handles accents, background noise, and multiple languages well.
Do you store my audio?: No. Files are processed in memory and immediately discarded. Nothing is saved.
Can I transcribe video files?: Yes. Upload MP4, WEBM, or any video format. The audio track is automatically extracted and transcribed.