Create a voice clone from an audio file upload

Creates a new voice clone by uploading an audio file directly. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best results, provide 5–10 seconds of clear speech. Maximum file size: 5MB for Telnyx, 20MB for Minimax.

POST /voice_clones/from_upload

JavaScript

JavaScript

import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});

const response = await client.voiceClones.createFromUpload({
  params: {
    audio_file: fs.createReadStream('path/to/file'),
    gender: 'male',
    language: 'lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf',
    name: 'name',
    provider: 'telnyx',
  },
});

console.log(response.data);

import os
from telnyx import Telnyx

client = Telnyx(
    api_key=os.environ.get("TELNYX_API_KEY"),  # This is the default and can be omitted
)
response = client.voice_clones.create_from_upload(
    params={
        "audio_file": b"Example data",
        "gender": "male",
        "language": "lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf",
        "name": "name",
        "provider": "telnyx",
    },
)
print(response.data)

package main

import (
	"bytes"
	"context"
	"fmt"
	"io"

	"github.com/team-telnyx/telnyx-go"
	"github.com/team-telnyx/telnyx-go/option"
)

func main() {
	client := telnyx.NewClient(
		option.WithAPIKey("My API Key"),
	)
	response, err := client.VoiceClones.NewFromUpload(context.TODO(), telnyx.VoiceCloneNewFromUploadParams{
		OfTelnyxQwen3TtsClone: &telnyx.VoiceCloneNewFromUploadParamsParamsTelnyxQwen3TtsClone{
			AudioFile: io.Reader(bytes.NewBuffer([]byte("Example data"))),
			Gender:    "male",
			Language:  "lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf",
			Name:      "name",
			Provider:  "telnyx",
		},
	})
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("%+v\n", response.Data)
}

package com.telnyx.sdk.example;

import com.telnyx.sdk.client.TelnyxClient;
import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient;
import com.telnyx.sdk.models.voiceclones.VoiceCloneCreateFromUploadParams;
import com.telnyx.sdk.models.voiceclones.VoiceCloneCreateFromUploadResponse;
import java.io.ByteArrayInputStream;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        TelnyxClient client = TelnyxOkHttpClient.fromEnv();

        VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone params = VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.builder()
            .audioFile(new ByteArrayInputStream("Example data".getBytes()))
            .gender(VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.Gender.MALE)
            .language("lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf")
            .name("name")
            .provider(VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.Provider.TELNYX)
            .build();
        VoiceCloneCreateFromUploadResponse response = client.voiceClones().createFromUpload(params);
    }
}

require "telnyx"

telnyx = Telnyx::Client.new(api_key: "My API Key")

response = telnyx.voice_clones.create_from_upload(
  params: {
    audio_file: StringIO.new("Example data"),
    gender: :male,
    language: "lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf",
    name: "name",
    provider: :telnyx
  }
)

puts(response)

<?php

require_once dirname(__DIR__) . '/vendor/autoload.php';

use Telnyx\Client;
use Telnyx\Core\FileParam;
use Telnyx\Core\Exceptions\APIException;

$client = new Client(apiKey: getenv('TELNYX_API_KEY') ?: 'My API Key');

try {
  $response = $client->voiceClones->createFromUpload(
    params: [
      'audioFile' => FileParam::fromString('Example data', filename: uniqid('file-upload-', true)),
      'gender' => 'male',
      'language' => 'lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf',
      'name' => 'name',
      'provider' => 'telnyx',
      'label' => 'label',
      'modelID' => 'Qwen3TTS',
      'refText' => 'ref_text',
    ],
  );

  var_dump($response);
} catch (APIException $e) {
  echo $e->getMessage();
}

telnyx voice-clones create-from-upload \
  --api-key 'My API Key' \
  --params '{audio_file: Example data, gender: male, language: lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf, name: name, provider: telnyx}'

curl --request POST \
  --url https://api.telnyx.com/v2/voice_clones/from_upload \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'audio_file=<string>' \
  --form 'name=<string>' \
  --form 'language=<string>' \
  --form 'ref_text=<string>' \
  --form 'label=<string>' \
  --form 0.audio_file='@example-file' \
  --form 1.audio_file='@example-file' \
  --form 2.audio_file='@example-file'

201

{
  "data": {
    "record_type": "voice_clone",
    "id": "660f9511-f3ac-52e5-b827-557766551111",
    "source_voice_design_id": "550e8400-e29b-41d4-a716-446655440000",
    "source_voice_design_version": 1,
    "name": "clone-narrator",
    "language": "en",
    "gender": "male",
    "label": "Speak in a warm, friendly tone",
    "created_at": "2024-01-01T00:00:00Z",
    "updated_at": "2024-01-01T00:00:00Z",
    "provider": "Telnyx",
    "provider_supported_models": [
      "Qwen3TTS"
    ],
    "provider_voice_id": "660f9511-f3ac-52e5-b827-557766551111",
    "model_id": "Qwen3TTS",
    "status": "active"
  }
}

{
  "data": {
    "record_type": "voice_clone",
    "id": "660f9511-f3ac-52e5-b827-557766551111",
    "source_voice_design_id": "550e8400-e29b-41d4-a716-446655440000",
    "source_voice_design_version": 1,
    "name": "clone-narrator",
    "language": "en",
    "gender": "male",
    "label": "Speak in a warm, friendly tone",
    "created_at": "2024-01-01T00:00:00Z",
    "updated_at": "2024-01-01T00:00:00Z",
    "provider": "Telnyx",
    "provider_supported_models": [
      "Qwen3TTS"
    ],
    "provider_voice_id": "660f9511-f3ac-52e5-b827-557766551111",
    "model_id": "Qwen3TTS",
    "status": "active"
  }
}

{
  "errors": [
    {
      "code": "10005",
      "title": "Resource not found",
      "detail": "Voice design not found"
    }
  ]
}

{
  "errors": [
    {
      "code": "10005",
      "title": "Resource not found",
      "detail": "Voice design not found"
    }
  ]
}

{
  "errors": [
    {
      "code": "10005",
      "title": "Resource not found",
      "detail": "Voice design not found"
    }
  ]
}

{
  "errors": [
    {
      "code": "10005",
      "title": "Resource not found",
      "detail": "Voice design not found"
    }
  ]
}

Authorizations

Authorization · string · header · required

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

Body

multipart/form-data

Option 1

Option 2

Option 3

Multipart form data for creating a voice clone from a direct audio upload. Maximum file size: 5MB for Telnyx, 20MB for Minimax.

audio_file · file · required

Audio file to clone the voice from. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best quality, provide 5–10 seconds of clear, uninterrupted speech. Maximum size: 5MB.

name · string · required

Name for the voice clone.

Maximum string length: 255

language · string · required

ISO 639-1 language code from the Qwen language set.

Pattern: ^([Aa]uto|[a-z]{2,3}(-[A-Za-z0-9]{2,8})*)$

gender · enum<string> · required

Gender of the voice clone.

Available options: male, female, neutral

provider · enum<string> · required

Voice synthesis provider. Must be telnyx.

Available options: telnyx, Telnyx

ref_text · string

Optional transcript of the audio file. Providing this improves clone quality.

label · string

Optional custom label describing the voice style.

model_id · enum<string> | null

TTS model identifier. Nullable/omittable — defaults to Qwen3TTS.

Available options: Qwen3TTS, null

Response

201

application/json

Voice clone created successfully from the uploaded audio.

Response envelope for a single voice clone.

data · object

A voice clone object.

Show child attributes