오디오

음성 복제

Clone a voice from an audio sample. Returns a voice handle (vv_...) that can be passed to POST /v1/audio/speech as the voice parameter to synthesize speech in the cloned voice; the handle must be paired with the same model used to create it.

Supported models:

tts-chatterbox-hd (Resemble AI) — accepts MP3, WAV, FLAC, and M4A samples. Zero-shot: no persistent voice template is derived; the reference audio is uploaded to a TTL’d storage object and re-read on each synthesis call. Handles expire automatically after 7 days. Available to regular users.
tts-minimax-speech-02-hd (MiniMax) — accepts MP3 and WAV only. Persistent: the upstream provider derives a custom voice template that survives across synthesis calls. Auto-deleted after 7 days without use; each successful TTS request resets the window. Currently limited access — contact [email protected] if you need it enabled.

Samples in containers outside the per-model allowlist are rejected with HTTP 400 before any upload.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST

audio

voices

/api/v1/audio/voices

curl --request POST \
  --url https://api.venice.ai/api/v1/audio/voices \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@example-file \
  --form model=tts-chatterbox-hd

import requests

url = "https://api.venice.ai/api/v1/audio/voices"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "model": "tts-chatterbox-hd" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('model', 'tts-chatterbox-hd');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.venice.ai/api/v1/audio/voices', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/audio/voices",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.venice.ai/api/v1/audio/voices"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/audio/voices")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/audio/voices")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "id": "vv_voice_abc123xyz",
  "model": "tts-chatterbox-hd"
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "code": "PAYLOAD_TOO_LARGE",
  "error": "File exceeds the maximum allowed size of 25 MB."
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

오디오 샘플을 업로드하여 복제된 음성 핸들을 생성한 다음, 생성할 때 사용한 것과 동일한 model과 함께 /audio/speech에 voice로 전달하세요. 단계별 안내는 음성 복제 가이드를 참조하세요.

인증

Authorization

string

header

필수

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

본문

multipart/form-data

Request to create a cloned voice from an audio sample. The returned vv_<id> handle is passed back as the voice parameter on POST /v1/audio/speech.

file

The voice sample audio file (multipart/form-data, field name "file"). Accepted containers depend on the selected model: tts-chatterbox-hd accepts MP3, WAV, FLAC, and M4A; tts-minimax-speech-02-hd accepts MP3 and WAV only. Recommended: a clean speech recording of at least 5–10 seconds.

model

enum<string>

기본값:tts-chatterbox-hd

The Venice TTS model the cloned voice will be paired with. The returned voice handle is only valid against this model on POST /v1/audio/speech.

사용 가능한 옵션:

tts-chatterbox-hd,

tts-minimax-speech-02-hd

예시:

"tts-chatterbox-hd"

응답

Voice cloned successfully

string

필수

The cloned voice handle. Pass this to POST /v1/audio/speech as the voice parameter alongside the same model used to create it. Handles expire automatically after the per-model retention window (currently 7 days for both supported models); for tts-minimax-speech-02-hd each successful TTS request resets that window.

예시:

"vv_voice_abc123xyz"

model

string

필수

The Venice TTS model this voice can be used with.

예시:

"tts-chatterbox-hd"

⌘I

/api/v1/audio/voices

curl --request POST \
  --url https://api.venice.ai/api/v1/audio/voices \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@example-file \
  --form model=tts-chatterbox-hd

import requests

url = "https://api.venice.ai/api/v1/audio/voices"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "model": "tts-chatterbox-hd" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('model', 'tts-chatterbox-hd');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.venice.ai/api/v1/audio/voices', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/audio/voices",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.venice.ai/api/v1/audio/voices"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/audio/voices")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/audio/voices")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\ntts-chatterbox-hd\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "id": "vv_voice_abc123xyz",
  "model": "tts-chatterbox-hd"
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "code": "PAYLOAD_TOO_LARGE",
  "error": "File exceeds the maximum allowed size of 25 MB."
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}