Seedream 5.0 Pro 정식 출시 | 이미지 생성기에서 사용해보기 →

Zonos2 Voice Cloning Text to Speech API

wavespeed-ai /

Zonos2 is a fast multilingual voice-cloning text-to-speech model that generates natural speech from text using a short reference audio sample. Ready-to-use REST inference API for voice cloning, multilingual TTS, narration, dubbing, character dialogue, virtual assistants, creator content, and professional speech generation workflows with simple integration, no coldstarts, and affordable pricing.

audio-to-audio
입력

대기 중

$0.01실행당·~100 / $1

예시전체 보기

관련 모델

README

Zonos2 Voice Cloning Text-to-Speech

Zonos2 Voice Cloning Text-to-Speech is an open-source, real-time text-to-speech model from Zyphra. It clones a voice from a short reference audio sample and synthesizes the supplied text in the cloned voice.

Why Choose This?

  • Voice cloning from reference audio
    Clone a speaker's voice from a short audio sample and generate speech from text.

  • Real-time text-to-speech model
    Built on Zonos2, an open-source real-time TTS model from Zyphra.

  • Background cleanup option
    Use clean_speaker_background when the reference audio has a clean background.

  • Standard audio output
    The generated audio is returned as a URL in the standard WaveSpeed prediction response.

Parameters

ParameterRequiredDescription
audioYesReference audio URL used to clone the voice. A short, clear sample works best.
textYesText to synthesize in the cloned voice.
clean_speaker_backgroundNoEnable when the reference audio has a clean background.

How to Use

  1. Upload reference audio — Provide a short, clear audio sample of the speaker voice you want to clone.
  2. Enter text — Provide the text that should be spoken in the cloned voice.
  3. Set background option (optional) — Enable clean_speaker_background when the reference audio has a clean background.
  4. Submit — Generate the cloned-voice speech output.

Output

Returns generated audio URL(s) in the standard WaveSpeed prediction response.

The generated audio is returned as WAV, 44.1kHz mono.

Pricing

Pricing is $0.01 per minute.

Reference Audio DurationBilled MinutesPrice
0-60s1$0.01
61-120s2$0.02
121-180s3$0.03

Billing Rules

  • Billing is based on the reference audio duration.
  • Reference audio duration is rounded up to the next full minute.
  • Minimum billing duration is 1 minute.
  • Each billed minute costs $0.01.

Best Use Cases

  • Voice cloning TTS — Generate speech in a cloned voice from a reference audio sample.
  • Narration generation — Create spoken narration from text using a target speaker voice.
  • Dialogue prototyping — Test voice lines, character speech, or script variations.
  • Localized speech generation — Use supported language normalization codes for multilingual text handling.
  • Audio content creation — Generate voice audio for videos, demos, apps, or creative workflows.

Pro Tips

  • Use clean reference audio with minimal background noise for better cloning quality.
  • Use a short and clear speaker sample for more stable voice cloning.
  • Make sure the reference audio contains the target speaker clearly.
  • Enable clean_speaker_background only when the reference audio has a clean background.
  • Ensure the audio URL is publicly accessible.

Notes

  • audio and text are required fields.
  • Provider sampling settings use the default mapping values.
참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Zonos2 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/zonos2 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Zonos2 below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "text": "A clear example input",
    "clean_speaker_background": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/zonos2" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/zonos2";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "text": "A clear example input",
        "clean_speaker_background": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "text": "A clear example input",
    "clean_speaker_background": False
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/zonos2", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Zonos2 API — Frequently asked questions

What is the Zonos2 API?

Zonos2 is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Zonos2 is a fast multilingual voice-cloning text-to-speech model that generates natural speech from text using a short reference audio sample. Ready-to-use REST inference API for voice cloning, multilingual TTS, narration, dubbing, character dialogue, virtual assistants, creator content, and professional speech generation workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Zonos2 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/zonos2.

How much does Zonos2 cost per run?

Zonos2 starts at $0.010 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Zonos2 accept?

Key inputs: `audio`, `clean_speaker_background`, `text`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/zonos2.

How long does Zonos2 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 555 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Zonos2 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.