Python SDK

pip install kova-tts

import os
from kova_tts import KovaTTSClient

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

client = KovaTTSClient(
    api_key=os.environ["KOVA_API_KEY"],
    base_url="https://staging.api.kova.ai/v1/tts",
)

from kova_tts import AudioResponseFormat

result = client.tts(
    text="Hello world.",
    voice="cal",
    response_format=AudioResponseFormat(encoding="mp3"),
    timestamps=True,
)

client.write_audio_file(result.audio, "out.mp3")
if result.timestamps:
    print(result.timestamps.words)

import asyncio
from kova_tts import AudioResponseFormat

async def main():
    async for event in client.stream_tts(
        text="Hello world.",
        voice="cal",
        response_format=AudioResponseFormat(encoding="mp3"),
        timestamps=True,
    ):
        if event.type == "audio":
            # event.audio is decoded bytes for this chunk
            print(f"audio: {len(event.audio)} bytes")
        elif event.type == "timestamps":
            print(event.words)

asyncio.run(main())

import asyncio
from kova_tts import AudioResponseFormat

async def main():
    async with client.websocket() as ws:
        await ws.start_context(
            context_id="ctx-1",
            voice_id="cal",
            model_id="default",
            response_format=AudioResponseFormat(encoding="pcm", sample_rate=32000),
        )
        await ws.send_text("Hello ", context_id="ctx-1")
        await ws.send_text("world.", context_id="ctx-1")
        await ws.flush(context_id="ctx-1", flush_id="end")

        async for frame in ws:
            if frame.type == "audio":
                print(f"pcm: {len(frame.audio)} bytes")
            elif frame.type == "timestamps":
                print(frame.timestamps.words)
            elif frame.type == "flush_completed" and frame.flush_id == "end":
                break

        await ws.close_context(context_id="ctx-1")

asyncio.run(main())

import wave
with wave.open("out.wav", "wb") as wf:
    wf.setnchannels(1)
    wf.setsampwidth(2)
    wf.setframerate(32000)
    wf.writeframes(pcm_bytes)

import httpx, os
resp = httpx.get("https://api.kova.ai/v1/tts/speakers",
                 headers={"x-api-key": os.environ["KOVA_API_KEY"]})
print(resp.json()["speaker_ids"])

from kova_tts import KovaTTSClient, KovaTTSError

try:
    result = client.tts(text="hi", voice="bad-voice")
except KovaTTSError as e:
    print(e.status_code, e.body)  # e.g. 422 {'detail': [...]}