Text to Speech
TTS API
API-key required
TTS API Tester
Test the public text-to-speech API with selectable language, model, voice, and reference parameters.
Supported endpoints
- POST /api/tts/v1/custom-voices
- POST /api/tts/v1/audio/speech
- GET /api/tts/v1/audio/speech/{taskId}
Selectable controls
Language changes filter the model list to compatible choices. Optional reference paths can use uploaded custom_voices/...references, same-site /uploads/...files, or saved voice paths.
Reference upload sample
Register a WAV and reuse the returned clone audio path.
curl -sS \
-X POST \
-H "x-api-key: YOUR_API_KEY" \
-F "audio_file=@/path/to/reference.wav" \
-F "model=cosytts" \
-F "language=en" \
-F "transcript=reference transcript here" \
"https://www.kaleidovid.com/api/tts/v1/custom-voices"Speech sample
Server-to-server request against the public TTS API.
curl -sS \
-X POST \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"text": "Hello from KaleidoVid. This is a short TTS API test.",
"language": "en",
"model": "cosytts",
"speaker": "Ryan"
}' \
"https://www.kaleidovid.com/api/tts/v1/audio/speech"Status sample
Poll the task ID returned by the speech call.
curl -sS \
-H "x-api-key: YOUR_API_KEY" \
"https://www.kaleidovid.com/api/tts/v1/audio/speech/{taskId}"Live tester
Paste a raw team API key, select language and model settings, then submit a real TTS request.
52/200 characters
Live response
{
"message": "Response JSON will appear here."
}