voxify

Convert plain text or Markdown into spoken audio and WebVTT subtitles.

Request

Send JSON to generate audio

Headers

Content-Type: application/json
Accept: application/json

Body

{
  "text": "Your text or markdown content here",
  "refresh": false
}

Send a JSON payload with a text field containing the text or Markdown content to synthesize. For Markdown inputs, front matter is parsed automatically.

The optional refresh field (default false) ignores any cached response for this text: the audio is synthesized again and replaces the cached entry.

Response

Receive audio and subtitles

JSON Payload

{
  "audio_base64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYx...", // Base64 encoded MP3 audio
  "vtt": "WEBVTT\n\n00:00.000 --> 00:01.000\nHello"  // WebVTT subtitles
}

The audio_base64 field contains MP3 audio encoded as base64. The vtt field contains subtitle cues in WebVTT format.

Notes

The API currently returns the full audio payload in a single JSON response. For large inputs, expect larger response sizes and longer processing times.

Responses may be cached: sending the exact same text again returns the stored result immediately. The X-Cache response header is HIT (served from cache), MISS (freshly synthesized), REFRESH (cache ignored on request, entry replaced) or BYPASS (cache disabled).

Example

cURL

curl -X POST https://voxify-labs.gaidot.net/api/synthesize \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello, this is a text-to-speech synthesis test."
  }'