Privacy Notice: Your audio/video files are sent to Fireworks AI API for transcription. When diarization is enabled, files are sent to AssemblyAI (transcripts are deleted immediately after processing). Data is not stored by the API providers. If you prefer local on-premises processing for sensitive content (e.g., FERPA-protected student data, IRB-approved research, HIPAA, or PII), please contact us at ailab@gc.cuny.edu.
Audio Transcription Upload audio or video files to generate automated transcriptions with optional speaker identification. Important: All AI-generated transcriptions should be reviewed manually for accuracy before use.
📁
Drag & drop a file here, or click to browse
Supports MP3, M4A, WAV, MP4, and other audio/video formats
⚠️ Maximum file size: 1GB. Large files may take several minutes to process.
Advanced Settings
Automatically identify different speakers in the recording (e.g., interviewer vs. interviewee). Uses AssemblyAI for best-in-class diarization accuracy on files of any length.
Speaker identification uses AssemblyAI for best-in-class diarization accuracy.