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:Documentation Index
Fetch the complete documentation index at: https://docs.kova.ai/llms.txt
Use this file to discover all available pages before exploring further.
| Transport | When to use | Time to first audio |
|---|---|---|
Sync HTTP (POST /v1/tts) | One-shot generation, batch jobs, when you want a single audio file at the end | Total generation time |
Streaming HTTP (POST /v1/tts/stream) | Playing audio as it’s generated for a single utterance | First audio chunk in ~200ms |
WebSocket (WS /v1/tts/ws) | Interactive applications (voice agents, dialog systems) — feed text incrementally, generate multiple utterances over one connection | First audio chunk in ~200ms; subsequent utterances reuse the warm connection |
x-api-key header), and the same billing.
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.