Welcome

Upload File: Click "Select File" to choose an existing audio/video file, then click "Start Transcription".

Record Audio: Click "Record" to use your microphone. When finished, you can "Stop" to preview or "Stop & Process" to immediately transcribe.

Supported Formats: MP3, MP4, M4A, WAV, WebM.

API Keys: Manage your ElevenLabs API keys here. You can add multiple keys and activate one at a time.

AI App: Choose which app to open (Gemini/ChatGPT) when using the "AI Post-Processing" feature.

Debug Mode: Enable this to see detailed logs in the server console (useful for troubleshooting).

After transcription, you can click "AI Post-Processing". This will:

1. Copy the transcript + a predefined prompt to your clipboard.
2. Open your selected AI app (Gemini or ChatGPT).
3. You can then simply paste to get a summary or analysis.

Tag Audio Events: Detects and labels non-speech sounds like [laughter], [applause], or [music].

Speaker ID (Diarization): Distinguishes between different speakers in the audio (e.g., Speaker A, Speaker B).

Output Format:

• TXT: Plain text transcript.
• SRT: Subtitles with precise timestamps (useful for video editing).

Auto-Record: Add ?rec_now to the URL to start recording immediately upon loading.

Auto-Login: Add ?auth_code=YOUR_KEY to log in automatically.

Combine: Use /?auth_code=...&rec_now to log in and start recording instantly!

Best Accuracy: Clear, high-quality audio yields the best transcriptions. Background noise can affect results.

Mobile: Add this page to your Home Screen for a native app-like experience (fullscreen, no browser bars).