Start with your recording
Upload your recording in one of the formats listed by the audio tool. Choose the spoken language and timestamp option before converting.
What the transcript contains
The default output is a Markdown transcript with punctuated paragraphs and optional [MM:SS] timestamps. It does not identify speakers. AI enhancement is optional and can add a summary, topic headings and extracted notes; review those additions against the recording.
Review and reuse
Check names, numbers and quotations against the recording. Noise, overlapping voices and unclear speech can cause transcription errors. The tool does not transcribe visual-only slide content or identify speakers.
Your plan sets file-size and duration limits. Uploaded files and conversion results are removed within one hour.