Instant voice cloning

from fishaudio import FishAudio
from fishaudio.types import ReferenceAudio
from fishaudio.utils import save

client = FishAudio()

with open("reference.wav", "rb") as f:
    audio = client.tts.convert(
        text="This sentence is spoken in the cloned voice.",
        references=[ReferenceAudio(
            audio=f.read(),
            text="Exact transcript of what is said in reference.wav.",
        )],
        model="s2.1-pro-free",
    )

save(audio, "cloned.mp3")

import asyncio
from fishaudio import AsyncFishAudio
from fishaudio.types import ReferenceAudio
from fishaudio.utils import save

async def main():
    async with AsyncFishAudio() as client:
        with open("reference.wav", "rb") as f:
            audio = await client.tts.convert(
                text="This sentence is spoken in the cloned voice.",
                references=[ReferenceAudio(
                    audio=f.read(),
                    text="Exact transcript of what is said in reference.wav.",
                )],
                model="s2.1-pro-free",
            )
    save(audio, "cloned.mp3")

asyncio.run(main())

import { FishAudioClient } from "fish-audio";
import { readFile, writeFile } from "fs/promises";

const client = new FishAudioClient({ apiKey: process.env.FISH_API_KEY });

const reference = new File(
  [await readFile("reference.wav")],
  "reference.wav",
);

const stream = await client.textToSpeech.convert(
  {
    text: "This sentence is spoken in the cloned voice.",
    references: [
      {
        audio: reference,
        text: "Exact transcript of what is said in reference.wav.",
      },
    ],
    format: "mp3",
  },
  "s2.1-pro-free",
);

const chunks = [];
for await (const chunk of stream) chunks.push(Buffer.from(chunk));

await writeFile("cloned.mp3", Buffer.concat(chunks));