AI-Powered Audio Toolkit

Transcribe audio.
Generate natural speech.

VoxNote turns your audio into timestamped text, and converts any text — even full chapters — into natural narrated audio.

10 free credits · No card required

Transcribe

Upload any audio file and get accurate text with precise timestamps, speaker labels, and export to TXT or SRT.

Paste any text — even a full book chapter — and get natural narrated audio from 30 hand-picked voices.

No bloat. Just the tools that matter for audio workflows.

Timestamped transcripts

Every segment gets precise start/end times you can export as SRT.

Auto language detection

Supports MP3, WAV, M4A, OGG, FLAC, WebM — any language.

30 natural voices

Bright, gravelly, warm, soft — pick the exact character for your audio.

Chunked long-form TTS

No length limit. Long articles and book chapters are chunked automatically.

Fast or Accurate mode

Optimise for speed or grammar-corrected, precise timestamps.

Export anywhere

Download TXT, SRT, or WAV files — no locked-in formats.

10 free credits on sign-up. No card required.