Clone a voice and wait until it is ready

import time

from fishaudio import FishAudio
from fishaudio.utils import save

client = FishAudio()

# 1. Create a persistent voice from a reference clip.
with open("reference.wav", "rb") as f:
    voice = client.voices.create(title="My Voice", voices=[f.read()])

# 2. Poll until the voice finishes training.
deadline = time.time() + 300  # 5-minute timeout
while voice.state != "trained":
    if voice.state == "failed":
        raise RuntimeError(f"Voice {voice.id} failed to train")
    if time.time() > deadline:
        raise TimeoutError(f"Voice {voice.id} not ready (state={voice.state})")
    time.sleep(5)
    voice = client.voices.get(voice.id)

# 3. Synthesize with the trained voice.
audio = client.tts.convert(
    text="My voice is ready to use.",
    reference_id=voice.id,
)
save(audio, "out.mp3")

import asyncio

from fishaudio import AsyncFishAudio
from fishaudio.utils import save


async def main():
    async with AsyncFishAudio() as client:
        # 1. Create a persistent voice from a reference clip.
        with open("reference.wav", "rb") as f:
            voice = await client.voices.create(title="My Voice", voices=[f.read()])

        # 2. Poll until the voice finishes training.
        deadline = asyncio.get_event_loop().time() + 300  # 5-minute timeout
        while voice.state != "trained":
            if voice.state == "failed":
                raise RuntimeError(f"Voice {voice.id} failed to train")
            if asyncio.get_event_loop().time() > deadline:
                raise TimeoutError(f"Voice {voice.id} not ready (state={voice.state})")
            await asyncio.sleep(5)
            voice = await client.voices.get(voice.id)

        # 3. Synthesize with the trained voice.
        audio = await client.tts.convert(
            text="My voice is ready to use.",
            reference_id=voice.id,
        )
    save(audio, "out.mp3")


asyncio.run(main())

import { readFile, writeFile } from "fs/promises";

import { FishAudioClient } from "fish-audio";

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

// 1. Create a persistent voice from a reference clip.
const sample = new File([await readFile("reference.wav")], "reference.wav");
let voice = await client.voices.ivc.create({
  title: "My Voice",
  visibility: "private",
  voices: [sample],
});

// 2. Poll until the voice finishes training.
const deadline = Date.now() + 300_000; // 5-minute timeout
while (voice.state !== "trained") {
  if (voice.state === "failed") {
    throw new Error(`Voice ${voice._id} failed to train`);
  }
  if (Date.now() > deadline) {
    throw new Error(`Voice ${voice._id} not ready (state=${voice.state})`);
  }
  await new Promise((resolve) => setTimeout(resolve, 5000));
  voice = await client.voices.get(voice._id);
}

// 3. Synthesize with the trained voice.
const stream = await client.textToSpeech.convert(
  { text: "My voice is ready to use.", reference_id: voice._id },
  "s2-pro",
);
const chunks = [];
for await (const chunk of stream) chunks.push(Buffer.from(chunk));
await writeFile("out.mp3", Buffer.concat(chunks));