Text-to-speech API
Text-to-speech, one API key
Turn text into natural, expressive speech across the best voice models — ElevenLabs and MiniMax — through one OpenAI-compatible endpoint and one balance. Multilingual, low-latency, billed per character of input.
POST /v1/audio/speech · $0.50 free credit, no card
6 models, one API key
Switch models with a string. Billed per use, refunded on failure.
Quick start
OpenAI-compatible. Point your client at https://kymaapi.com/v1 with a ky- key.
curl https://kymaapi.com/v1/audio/speech \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eleven-flash-v2-5",
"input": "Hello from Kyma — one API for every model.",
"voice": "rachel"
}' --output speech.mp3FAQ
Which text-to-speech models does Kyma support?
Kyma serves ElevenLabs (Multilingual v2, Flash v2.5, Turbo v2.5) and MiniMax Speech (HD and Turbo) through one API. Switch between them by changing the model string — same key, same endpoint.
How much does text-to-speech cost?
TTS is billed per 1,000 characters of input text, charged only on successful synthesis. There is no subscription. See the pricing page for per-model rates.
Is the speech API OpenAI-compatible?
Yes. Call POST /v1/audio/speech with a model, input text, and voice, the same shape as the OpenAI speech API, and receive an audio file back.
Can I clone voices or design new ones?
Yes — voice cloning and voice design are available through the audio API in addition to the standard preset voices. See the audio docs for the voice-clone and voice-design endpoints.
$0.50 free credit on signup. No credit card required.
Get your free API key →