Transcription

Transcription (Speech-to-Text) converts audio files into text. GhostMind’s transcription service processes audio through your connected AI provider accounts.

Using Transcription

In the Playground

1. Navigate to Playground → Transcription
2. Upload an audio file (or drag and drop)
3. Optionally specify a language
4. Click Transcribe
5. The transcript appears in the text area
6. Use the Copy button to copy the text

Note

Transcription does not auto-send the transcript to chat. You decide what to do with the text.

Privacy

GhostMind’s transcription service is privacy-first:

• No transcript storage — The transcript text is returned to you but never stored in the database
• No raw audio logging — Audio files are deleted immediately after transcription
• Metrics only — Only metadata (mime type, size, language, duration, status) is recorded

Supported Formats

Common audio formats are supported including:

• MP3, WAV, M4A, OGG
• WebM, FLAC

Note

Format support depends on the provider. Check your provider’s documentation for details.

API Usage

curl https://ghostmind.optdmsa.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-gm-..." \
  -F "file=@audio.mp3" \
  -F "language=en"

See Audio Transcription API for the full reference.

Next Steps

• Speech Generation — Convert text to audio
• Audio Transcription API — API reference
• Playground — Try transcription in the UI