Turn Markdown into speech.
voxify converts texts, in plain text or Markdown format, into natural-sounding MP3 audio, with word-level WebVTT subtitles. Paste your text in the browser, or call the REST API from your own projects.
Features
Built for long-form content
Markdown aware
Formatting, links and code are cleaned before reading. The title from YAML front matter is read first.
Long articles
Text is split into chunks on natural boundaries, synthesized in sequence and merged into a single audio file.
Synchronized subtitles
Every result comes with WebVTT subtitles, highlighted in real time during playback.
Instant replays
A built-in caching system speeds up repeated requests.
How it works
From text to audio in three steps
-
01
Write or paste
Plain text or a full Markdown article, front matter included.
-
02
Generate
voxify cleans the text and synthesizes it with neural voices.
-
03
Listen and download
Play the result in the browser, then export the MP3 and VTT files.
For developers
Give your apps a voice with one API call
/api/synthesize
Integrate voxify into your own tools: send a JSON payload, get back base64 MP3 audio and WebVTT subtitles.
curl -X POST https://voxify-labs.gaidot.net/api/synthesize \
-H "Content-Type: application/json" \
-d '{ "text": "# Hello\nThis is voxify." }'