Create or add a version to a voice design

Creates a new voice design (version 1) when voice_design_id is omitted. When voice_design_id is provided, adds a new version to the existing design instead. A design can have at most 50 versions.

POST /voice_designs

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 voiceDesign = await client.voiceDesigns.create({
  prompt: 'Speak in a warm, friendly tone',
  text: 'Hello, welcome to our service.',
});

console.log(voiceDesign.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
)
voice_design = client.voice_designs.create(
    prompt="Speak in a warm, friendly tone",
    text="Hello, welcome to our service.",
)
print(voice_design.data)

package main

import (
	"context"
	"fmt"

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

func main() {
	client := telnyx.NewClient(
		option.WithAPIKey("My API Key"),
	)
	voiceDesign, err := client.VoiceDesigns.New(context.TODO(), telnyx.VoiceDesignNewParams{
		Prompt: "Speak in a warm, friendly tone",
		Text:   "Hello, welcome to our service.",
	})
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("%+v\n", voiceDesign.Data)
}

package com.telnyx.sdk.example;

import com.telnyx.sdk.client.TelnyxClient;
import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient;
import com.telnyx.sdk.models.voicedesigns.VoiceDesignCreateParams;
import com.telnyx.sdk.models.voicedesigns.VoiceDesignCreateResponse;

public final class Main {
    private Main() {}

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

        VoiceDesignCreateParams params = VoiceDesignCreateParams.builder()
            .prompt("Speak in a warm, friendly tone")
            .text("Hello, welcome to our service.")
            .build();
        VoiceDesignCreateResponse voiceDesign = client.voiceDesigns().create(params);
    }
}

require "telnyx"

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

voice_design = telnyx.voice_designs.create(
  prompt: "Speak in a warm, friendly tone",
  text: "Hello, welcome to our service."
)

puts(voice_design)

<?php

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

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

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

try {
  $voiceDesign = $client->voiceDesigns->create(
    prompt: 'Speak in a warm, friendly tone',
    text: 'Hello, welcome to our service.',
    language: 'Auto',
    maxNewTokens: 100,
    name: 'friendly-narrator',
    provider: 'telnyx',
    repetitionPenalty: 1,
    temperature: 0,
    topK: 1,
    topP: 0,
    voiceDesignID: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  );

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

telnyx voice-designs create \
  --api-key 'My API Key' \
  --prompt 'Speak in a warm, friendly tone' \
  --text 'Hello, welcome to our service.'

curl --request POST \
  --url https://api.telnyx.com/v2/voice_designs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "friendly-narrator",
  "text": "Hello, welcome to our service.",
  "prompt": "Speak in a warm, friendly tone",
  "language": "Auto",
  "provider": "telnyx"
}
'

201

{
  "data": {
    "record_type": "voice_design",
    "id": "550e8400-e29b-41d4-a716-446655440000",
    "name": "friendly-narrator",
    "version": 1,
    "text": "Hello, welcome.",
    "prompt": "Speak in a warm tone",
    "voice_sample_size": 48000,
    "version_created_at": "2024-01-01T00:00:00Z",
    "created_at": "2024-01-01T00:00:00Z",
    "updated_at": "2024-01-01T00:00:00Z",
    "provider": "Telnyx",
    "provider_supported_models": [
      "Qwen3TTS"
    ],
    "provider_voice_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

{
  "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"
    }
  ]
}

{
  "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

application/json

Request body for creating a new voice design or adding a version to an existing one. Omit voice_design_id to create a new design; include it to add a new version.

text · string · required

Sample text to synthesize for this voice design.

prompt · string · required

Natural language description of the voice style, e.g. 'Speak in a warm, friendly tone with a slight British accent'.

name · string

Name for the voice design. Required when creating a new design (voice_design_id is not provided); ignored when adding a version. Cannot be a UUID.

Required string length: 1 - 255

voice_design_id · string<uuid>

ID of an existing voice design to add a new version to. When provided, a new version is created instead of a new design.

language · string · default: Auto

Language for synthesis. Supported values: Auto, Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian. Defaults to Auto.

temperature · number<float>

Sampling temperature controlling randomness. Higher values produce more varied output. Default: 0.9.

Required range: 0 <= x <= 2

top_k · integer

Top-k sampling parameter — limits the token vocabulary considered at each step. Default: 50.

Required range: 1 <= x <= 1000

top_p · number<float>

Top-p (nucleus) sampling parameter — cumulative probability cutoff for token selection. Default: 1.0.

Required range: 0 <= x <= 1

repetition_penalty · number<float>

Repetition penalty to reduce repeated patterns in generated audio. Default: 1.05.

Required range: 1 <= x <= 2

max_new_tokens · integer

Maximum number of tokens to generate. Default: 2048.

Required range: 100 <= x <= 4096

provider · enum<string> · default: telnyx

Voice synthesis provider. telnyx uses the Qwen3TTS model; minimax uses the Minimax speech models. Case-insensitive. Defaults to telnyx.

Available options: telnyx, minimax, Telnyx, Minimax

Response

201

application/json

Voice design created or new version added successfully.

Response envelope for a single voice design with full version detail.

data · object

A voice design object with full version detail.

Show child attributes