Voice Transcription

What is Voice Transcription?

Voice transcription converts speech in audio files to text. Useful for documenting meeting recordings, interviews, lectures, and more.

Supported Formats

• MP3, WAV, M4A
• AAC, FLAC
• OGG, Opus

Transcribing Audio

From File Viewer

1. Open the audio file in the file viewer
2. Click the Transcribe button at the top
3. When transcription is complete, the result is displayed on screen
4. The transcribed text is saved as a file in the same folder

Request from AI

You can also request transcription directly from AI:

"Convert this meeting recording to text"

"Transcribe the interview audio"

Transcription Model Settings

Select the transcription model to use in Settings > AI Models > Transcription.

Additional Tasks

Use transcribed text for immediate follow-up tasks:

"Transcribe the meeting recording and summarize key points"

"Transcribe the interview and organize by topic"

Multilingual Support

Transcribe audio in various languages including Korean, English, and Japanese. AI automatically detects the language.

Credit Usage

Voice transcription uses an AI model, so it consumes credits.