We just added Capa Text to Speech to the Nabzclan Developer API. You can now turn text into spoken audio with Capa voices, simple API calls, raw MP3 downloads, and JSON/base64 responses for apps that need audio inside JSON payloads.

The endpoint is available now:

POST https://developer.nabzclan.vip/api/ai/v1/audio/speech

What You Can Build

  • AI voice replies for chatbots, assistants, support flows, and generated responses.
  • Accessibility features that read articles, docs, user messages, or dashboard content aloud.
  • Creator tooling for voiceovers, reels, shorts, podcast snippets, and product demos.
  • Education apps with pronunciation clips, lesson audio, flashcards, and language practice.
  • Voice alerts for monitoring, moderation, notifications, and workflow status updates.

Public Model IDs

Use the public Capa model format in your request body:

v1-capa-tts-nabzclan/{locale}-{VoiceName}Neural

Example:

v1-capa-tts-nabzclan/en-AU-NatashaNeural

Generate MP3 Audio

curl -X POST https://developer.nabzclan.vip/api/ai/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "v1-capa-tts-nabzclan/en-AU-NatashaNeural",
    "input": "Hello, this is a voice test generated with the Capa text to speech model by nabzclan."
  }' \
  --output speech.mp3

JSON/Base64 Mode

If your app prefers JSON, add ?response_format=json. This returns JSON containing base64 audio instead of a raw binary response.

curl -X POST "https://developer.nabzclan.vip/api/ai/v1/audio/speech?response_format=json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "v1-capa-tts-nabzclan/en-US-GuyNeural",
    "input": "Hello, this is a voice test generated with the Capa text to speech model by nabzclan."
  }'

Available Voices

The first Capa TTS release includes 19 voices across English and Spanish locales. Every voice has a generated MP3 sample in the docs so you can compare tone, pacing, accent, and pronunciation before choosing one.

  • English: Australia, Canada, Hong Kong, India, New Zealand, and United States voices.
  • Spanish: Argentina, Mexico, Puerto Rico, Spain, and Dominican Republic voices.
  • Samples: each voice sample uses the same phrase for easy comparison.

Find docs here →

Request Tracking

Capa Text to Speech is tracked as an AI endpoint. Requests count toward your plan's AI request limits, not the normal API usage bucket.

Need Another Voice?

If you need another voice or locale, open a ticket at helpdesk.nabzclan.vip. Send the voice or locale you want and the Nabzclan team will review it for addition.