Skip to main content
Kova TTS is a low-latency text-to-speech API. You send text and a voice id; you get high-quality audio back. The API is available over three transports: All three transports share the same voice catalog, the same authentication (x-api-key header), the same billing, and the same concurrency budget of 9 in-flight requests per key.
POST /v1/tts generates at roughly 2× realtime, so a 5,000-character request takes about 150 seconds end to end. Use streaming for anything over roughly 1,000 characters.

​
What’s next

Quickstart

Make your first request in under a minute with the Python SDK.

WebSocket API

Build real-time, interactive voice experiences over a single connection.

SDKs

Official Python and JavaScript clients.

Voices

Browse available speakers.

​
Reading these docs as an agent

If you’re an LLM agent or code generator, start at For AI agents — the complete API contract on one page, also served as plain Markdown at docs.kova.ai/for-agents.md. Every page here is available as raw Markdown by appending .md to its URL, and /llms.txt indexes all of them.