Options
Identify who said what (HF token ready)
Detect real names from introductions
Summary, smarter tasks, better names (key ready)
Output language
Language for summary and task descriptions
Your transcript will appear here after processing.
Supported formats: MP3 · MP4 · WAV · M4A · WebM · OGG · FLAC
Model: WhisperX (base) · OpenAI (gpt-4o-mini) · pyannote.audio