Skip to main content

​
1. Get an API key

Sign in at platform.kova.ai and create a key on the API keys page. Keys start with kova_sk_.
Keep your key secret. Anyone with the key can spend your credits.

​
2. Install the SDK

pip install kova-tts

npm install @kova-ai/tts

# Already on your machine.

​
3. Make your first request

import os
from kova_tts import KovaTTSClient, AudioResponseFormat

client = KovaTTSClient(api_key=os.environ["KOVA_API_KEY"])

result = client.tts(
    text="Hello from Kova.",
    voice="cal",
    response_format=AudioResponseFormat(encoding="mp3"),
)

client.write_audio_file(result.audio, "out.mp3")
print("wrote out.mp3")

import { KovaTTSClient } from "@kova-ai/tts";

const client = new KovaTTSClient({ apiKey: process.env.KOVA_API_KEY! });

const result = await client.tts({
  text: "Hello from Kova.",
  voice: "cal",
  response_format: { encoding: "mp3" },
});

await client.writeAudioFile(result.audio, "out.mp3");
console.log("wrote out.mp3");

curl https://api.kova.ai/v1/tts \
  -H "x-api-key: $KOVA_API_KEY" \
  -H "content-type: application/json" \
  -d '{"text":"Hello from Kova.","voice":"cal","response_format":{"encoding":"mp3"}}' \
  | jq -r .audio | base64 -d > out.mp3

​
4. Play it

open out.mp3   # macOS
xdg-open out.mp3   # Linux
You should hear “Hello from Kova.” in the cal voice.

​
What’s next

Streaming TTS

Start playback before generation finishes.

WebSocket API

Real-time, multi-utterance voice experiences.

Voices

Browse all available speakers.

Authentication

Where keys come from and how to manage them.