SLNG

export SLNG_API_KEY="YOUR_SLNG_API_KEY"

curl --fail-with-body --request POST \
  --url "https://api.slng.ai/v1/tts/slng/fish/tts:s2.1-pro" \
  --header "Authorization: Bearer $SLNG_API_KEY" \
  --header "X-World-Part-Override: eu" \
  --header 'Content-Type: application/json' \
  --data '{
    "text": "Hello from Fish Audio on SLNG.",
    "reference_id": "9a9cf47702da476aa4629e2506d4a857",
    "format": "mp3"
  }' \
  --output output.mp3

import asyncio
import os

import msgpack
from websockets.asyncio.client import connect


async def tts_stream():
    url = "wss://api.slng.ai/v1/tts/slng/fish/tts:s2.1-pro"
    headers = {
        "Authorization": f"Bearer {os.environ['SLNG_API_KEY']}",
        "X-World-Part-Override": "eu",
    }

    async with connect(url, additional_headers=headers) as ws:
        # Start a session with the voice and output format.
        await ws.send(msgpack.packb({
            "event": "start",
            "request": {
                "text": "",
                "reference_id": "9a9cf47702da476aa4629e2506d4a857",
                "format": "mp3",
            },
        }, use_bin_type=True))

        # Send one or more text frames, then signal the end of input.
        await ws.send(msgpack.packb({
            "event": "text",
            "text": "Hello from Fish Audio on SLNG.",
        }, use_bin_type=True))
        await ws.send(msgpack.packb({"event": "stop"}, use_bin_type=True))

        with open("output.mp3", "wb") as output:
            async for message in ws:
                data = msgpack.unpackb(message, raw=False)

                if data["event"] == "audio":
                    output.write(data["audio"])
                elif data["event"] == "error":
                    raise RuntimeError(data["error"])
                elif data["event"] == "finish":
                    if data["reason"] == "error":
                        raise RuntimeError("SLNG ended synthesis with an error")
                    break


asyncio.run(tts_stream())