MiniMax Speech-2.5-turbo-preview Async Text-to-Speech

POST /v3/async/minimax-speech-2.5-turbo-preview

MiniMax Speech-2.5-turbo-preview Async Text-to-Speech

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "text": "<string>",
  "voice_setting": {
    "speed": 123,
    "vol": 123,
    "pitch": 123,
    "voice_id": "<string>",
    "emotion": "<string>",
    "text_normalization": true
  },
  "audio_setting": {
    "sample_rate": 123,
    "bitrate": 123,
    "format": "<string>",
    "channel": 123
  },
  "pronunciation_dict": {
    "tone": [
      {}
    ]
  },
  "language_boost": "<string>",
  "voice_modify": {
    "pitch": 123,
    "intensity": 123,
    "timbre": 123,
    "sound_effects": "<string>"
  }
}
'

import requests

url = "https://api.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview"

payload = {
    "text": "<string>",
    "voice_setting": {
        "speed": 123,
        "vol": 123,
        "pitch": 123,
        "voice_id": "<string>",
        "emotion": "<string>",
        "text_normalization": True
    },
    "audio_setting": {
        "sample_rate": 123,
        "bitrate": 123,
        "format": "<string>",
        "channel": 123
    },
    "pronunciation_dict": { "tone": [{}] },
    "language_boost": "<string>",
    "voice_modify": {
        "pitch": 123,
        "intensity": 123,
        "timbre": 123,
        "sound_effects": "<string>"
    }
}
headers = {
    "Content-Type": "<content-type>",
    "Authorization": "<authorization>"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
  body: JSON.stringify({
    text: '<string>',
    voice_setting: {
      speed: 123,
      vol: 123,
      pitch: 123,
      voice_id: '<string>',
      emotion: '<string>',
      text_normalization: true
    },
    audio_setting: {sample_rate: 123, bitrate: 123, format: '<string>', channel: 123},
    pronunciation_dict: {tone: [{}]},
    language_boost: '<string>',
    voice_modify: {pitch: 123, intensity: 123, timbre: 123, sound_effects: '<string>'}
  })
};

fetch('https://api.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview', 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.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'text' => '<string>',
    'voice_setting' => [
        'speed' => 123,
        'vol' => 123,
        'pitch' => 123,
        'voice_id' => '<string>',
        'emotion' => '<string>',
        'text_normalization' => true
    ],
    'audio_setting' => [
        'sample_rate' => 123,
        'bitrate' => 123,
        'format' => '<string>',
        'channel' => 123
    ],
    'pronunciation_dict' => [
        'tone' => [
                [
                                
                ]
        ]
    ],
    'language_boost' => '<string>',
    'voice_modify' => [
        'pitch' => 123,
        'intensity' => 123,
        'timbre' => 123,
        'sound_effects' => '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($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.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview"

	payload := strings.NewReader("{\n  \"text\": \"<string>\",\n  \"voice_setting\": {\n    \"speed\": 123,\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"voice_id\": \"<string>\",\n    \"emotion\": \"<string>\",\n    \"text_normalization\": true\n  },\n  \"audio_setting\": {\n    \"sample_rate\": 123,\n    \"bitrate\": 123,\n    \"format\": \"<string>\",\n    \"channel\": 123\n  },\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\n  },\n  \"language_boost\": \"<string>\",\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"intensity\": 123,\n    \"timbre\": 123,\n    \"sound_effects\": \"<string>\"\n  }\n}")

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

	req.Header.Add("Content-Type", "<content-type>")
	req.Header.Add("Authorization", "<authorization>")

	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.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"text\": \"<string>\",\n  \"voice_setting\": {\n    \"speed\": 123,\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"voice_id\": \"<string>\",\n    \"emotion\": \"<string>\",\n    \"text_normalization\": true\n  },\n  \"audio_setting\": {\n    \"sample_rate\": 123,\n    \"bitrate\": 123,\n    \"format\": \"<string>\",\n    \"channel\": 123\n  },\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\n  },\n  \"language_boost\": \"<string>\",\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"intensity\": 123,\n    \"timbre\": 123,\n    \"sound_effects\": \"<string>\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.myrouter.ai/v3/async/minimax-speech-2.5-turbo-preview")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n  \"text\": \"<string>\",\n  \"voice_setting\": {\n    \"speed\": 123,\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"voice_id\": \"<string>\",\n    \"emotion\": \"<string>\",\n    \"text_normalization\": true\n  },\n  \"audio_setting\": {\n    \"sample_rate\": 123,\n    \"bitrate\": 123,\n    \"format\": \"<string>\",\n    \"channel\": 123\n  },\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\n  },\n  \"language_boost\": \"<string>\",\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"intensity\": 123,\n    \"timbre\": 123,\n    \"sound_effects\": \"<string>\"\n  }\n}"

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

200

{
  "task_id": "<string>"
}

This API supports asynchronous text-to-speech generation with a maximum of 1 million characters per request. The complete generated audio result can be retrieved asynchronously. Supports 100+ system voices and cloned voices; supports customization of pitch, speed, volume, bitrate, sample rate, and output format.

After submitting a long text speech synthesis request, please note that the returned URL is valid for 24 hours from the time it is generated. Please download the content in time.

Suitable for long text speech generation such as entire books. Task queuing may take a long time. For short sentence generation, voice chat, and online social scenarios, it is recommended to use Synchronous Text-to-Speech.

Request Headers

Content-Type · string · required

Enum: application/json

Authorization · string · required

Bearer authentication format: Bearer {{API Key}}.

Request Body

text · string · required

The text to be synthesized, limited to a maximum of 50,000 characters.

voice_setting · object · required

Show properties

speed · number

Range [0.5, 2], Default: 1.0

The speech rate of the generated audio. Optional; higher values result in faster speech.

vol · number

Range (0, 10], Default: 1.0

The volume of the generated audio. Optional; higher values result in louder volume.

pitch · number · default: 0

Range [-12, 12], Default: 0

The pitch of the generated audio. Optional (0 outputs the original voice; value must be an integer).

voice_id · string

The voice ID for the request.

Supports both system voices (ID) and cloned voices (ID). The system voice IDs are as follows:

• Youthful Male Voice: male-qn-qingse
• Elite Young Male Voice: male-qn-jingying
• Assertive Young Male Voice: male-qn-badao
• College Male Voice: male-qn-daxuesheng
• Young Female Voice: female-shaonv
• Mature Female Voice (Confident): female-yujie
• Mature Female Voice: female-chengshu
• Sweet Female Voice: female-tianmei
• Male Presenter: presenter_male
• Female Presenter: presenter_female
• Male Audiobook 1: audiobook_male_1
• Male Audiobook 2: audiobook_male_2
• Female Audiobook 1: audiobook_female_1
• Female Audiobook 2: audiobook_female_2
• Youthful Male Voice-beta: male-qn-qingse-jingpin
• Elite Young Male Voice-beta: male-qn-jingying-jingpin
• Assertive Young Male Voice-beta: male-qn-badao-jingpin
• College Male Voice-beta: male-qn-daxuesheng-jingpin
• Young Female Voice-beta: female-shaonv-jingpin
• Mature Female Voice (Confident)-beta: female-yujie-jingpin
• Mature Female Voice-beta: female-chengshu-jingpin
• Sweet Female Voice-beta: female-tianmei-jingpin
• Smart Boy: clever_boy
• Cute Boy: cute_boy
• Adorable Girl: lovely_girl
• Cartoon Pig: cartoon_pig
• Cute Little Brother: bingjiao_didi
• Handsome Boyfriend: junlang_nanyou
• Innocent Junior: chunzhen_xuedi
• Cool Senior: lengdan_xiongzhang
• Assertive Young Master: badao_shaoye
• Sweet Ling: tianxin_xiaoling
• Playful Girl: qiaopi_mengmei
• Charming Lady: wumei_yujie
• Cute Junior Girl: diadia_xuemei
• Elegant Senior Girl: danya_xuejie
• Santa Claus: Santa_Claus
• Grinch: Grinch
• Rudolph: Rudolph
• Arnold: Arnold
• Charming Santa: Charming_Santa
• Charming Lady: Charming_Lady
• Sweet Girl: Sweet_Girl
• Cute Elf: Cute_Elf
• Attractive Girl: Attractive_Girl
• Serene Woman: Serene_Woman

emotion · string

Controls the emotion of the synthesized speech.

Currently supports 7 emotions: happy, sad, angry, fearful, disgusted, surprised, neutral.

Possible values: ["happy", "sad", "angry", "fearful", "disgusted", "surprised", "neutral"]

text_normalization · bool · default: "false"

This parameter enables English text normalization, which can improve performance in number reading scenarios but slightly increases latency. If not provided, defaults to false.

audio_setting · object

Show properties

sample_rate · number · default: 32000

Possible values: [8000, 16000, 22050, 24000, 32000, 44100]

The sample rate of the generated audio. Optional, Default: 32000.

bitrate · number · default: 128000

Possible values: [32000, 64000, 128000, 256000]

The bitrate of the generated audio. Optional, Default: 128000. This parameter only applies to mp3 format audio.

format · string · default: "mp3"

The format of the generated audio. Default: mp3. Options: mp3, pcm, flac, wav. wav is only supported in non-streaming output.

channel · number · default: 1

The number of audio channels. Default 1: mono. Options:

1: Mono

2: Stereo

pronunciation_dict · object

Show properties

tone · list

Replace characters, symbols, and their corresponding pronunciations that require special annotation.

Replace pronunciation (adjust tone/replace with other character pronunciation), format as follows:

["yan-shao-fei/(yan4)(shao3)(fei1)","da-fei/(da2)(fei1)","omg/oh my god"]

Tones are represented by numbers: 1st tone (high level) is 1, 2nd tone (rising) is 2, 3rd tone (dipping) is 3, 4th tone (falling) is 4, neutral tone is 5.

language_boost · string · default: "null"

Enhances recognition of specified minority languages and dialects. When set, it can improve speech performance for the specified language/dialect. If the language type is unclear, you can select “auto” and the model will automatically determine the language type. Supported values:

'Chinese', 'Chinese,Yue', 'English', 'Arabic', 'Russian', 'Spanish', 'French', 'Portuguese', 'German', 'Turkish', 'Dutch', 'Ukrainian', 'Vietnamese', 'Indonesian', 'Japanese', 'Italian', 'Korean', 'Thai', 'Polish', 'Romanian', 'Greek', 'Czech', 'Finnish', 'Hindi', 'Bulgarian', 'Danish', 'Hebrew', 'Malay', 'Persian', 'Slovak', 'Swedish', 'Croatian', 'Filipino', 'Hungarian', 'Norwegian', 'Slovenian', 'Catalan', 'Nynorsk', 'Tamil', 'Afrikaans', 'auto'

voice_modify · object

Voice effect settings. Supported audio formats for this parameter: mp3, wav, flac

Show properties

pitch · integer

Pitch adjustment (deep/bright), range [-100, 100]. Values closer to -100 produce a deeper sound; values closer to 100 produce a brighter sound.

intensity · integer

Intensity adjustment (powerful/soft), range [-100, 100]. Values closer to -100 produce a more powerful sound; values closer to 100 produce a softer sound.

timbre · integer

Timbre adjustment (rich/crisp), range [-100, 100]. Values closer to -100 produce a richer sound; values closer to 100 produce a crisper sound.

sound_effects · string

Sound effect settings. Only one can be selected at a time. Possible values:

• spacious_echo (Spacious Echo)
• auditorium_echo (Auditorium Broadcast)
• lofi_telephone (Telephone Distortion)
• robotic (Electronic Voice)

Response

task_id · string · required

The task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.