MiniMax Speech-02-turbo Synchronous Text-to-Speech

POST /v3/minimax-speech-02-turbo

MiniMax Speech-02-turbo Synchronous Text-to-Speech

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/minimax-speech-02-turbo \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "text": "<string>",
  "voice_setting": {
    "speed": 123,
    "vol": 123,
    "pitch": 123,
    "voice_id": "<string>",
    "emotion": "<string>",
    "latex_read": true,
    "text_normalization": true
  },
  "audio_setting": {
    "sample_rate": 123,
    "bitrate": 123,
    "format": "<string>",
    "channel": 123
  },
  "pronunciation_dict": {
    "tone": [
      {}
    ]
  },
  "timbre_weights": [
    {
      "voice_id": "<string>",
      "weight": 123
    }
  ],
  "stream": true,
  "stream_options": {
    "exclude_aggregated_audio": true
  },
  "language_boost": "<string>",
  "output_format": "<string>",
  "voice_modify": {
    "pitch": 123,
    "intensity": 123,
    "timbre": 123,
    "sound_effects": "<string>"
  }
}
'

import requests

url = "https://api.myrouter.ai/v3/minimax-speech-02-turbo"

payload = {
    "text": "<string>",
    "voice_setting": {
        "speed": 123,
        "vol": 123,
        "pitch": 123,
        "voice_id": "<string>",
        "emotion": "<string>",
        "latex_read": True,
        "text_normalization": True
    },
    "audio_setting": {
        "sample_rate": 123,
        "bitrate": 123,
        "format": "<string>",
        "channel": 123
    },
    "pronunciation_dict": { "tone": [{}] },
    "timbre_weights": [
        {
            "voice_id": "<string>",
            "weight": 123
        }
    ],
    "stream": True,
    "stream_options": { "exclude_aggregated_audio": True },
    "language_boost": "<string>",
    "output_format": "<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>',
      latex_read: true,
      text_normalization: true
    },
    audio_setting: {sample_rate: 123, bitrate: 123, format: '<string>', channel: 123},
    pronunciation_dict: {tone: [{}]},
    timbre_weights: [{voice_id: '<string>', weight: 123}],
    stream: true,
    stream_options: {exclude_aggregated_audio: true},
    language_boost: '<string>',
    output_format: '<string>',
    voice_modify: {pitch: 123, intensity: 123, timbre: 123, sound_effects: '<string>'}
  })
};

fetch('https://api.myrouter.ai/v3/minimax-speech-02-turbo', 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/minimax-speech-02-turbo",
  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>',
        'latex_read' => true,
        'text_normalization' => true
    ],
    'audio_setting' => [
        'sample_rate' => 123,
        'bitrate' => 123,
        'format' => '<string>',
        'channel' => 123
    ],
    'pronunciation_dict' => [
        'tone' => [
                [
                                
                ]
        ]
    ],
    'timbre_weights' => [
        [
                'voice_id' => '<string>',
                'weight' => 123
        ]
    ],
    'stream' => true,
    'stream_options' => [
        'exclude_aggregated_audio' => true
    ],
    'language_boost' => '<string>',
    'output_format' => '<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/minimax-speech-02-turbo"

	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    \"latex_read\": true,\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  \"timbre_weights\": [\n    {\n      \"voice_id\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"stream\": true,\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"language_boost\": \"<string>\",\n  \"output_format\": \"<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/minimax-speech-02-turbo")
  .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    \"latex_read\": true,\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  \"timbre_weights\": [\n    {\n      \"voice_id\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"stream\": true,\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"language_boost\": \"<string>\",\n  \"output_format\": \"<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/minimax-speech-02-turbo")

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    \"latex_read\": true,\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  \"timbre_weights\": [\n    {\n      \"voice_id\": \"<string>\",\n      \"weight\": 123\n    }\n  ],\n  \"stream\": true,\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"language_boost\": \"<string>\",\n  \"output_format\": \"<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

{
  "audio": "<string>",
  "status": 123
}

This API supports synchronous text-to-speech generation with a maximum of 10,000 characters per request. Supports 100+ system voices and cloned voices; supports volume, pitch, speed, and output format customization; supports proportional voice mixing and fixed interval time control; supports multiple audio specifications and formats including: mp3, pcm, flac, wav, with streaming output support.

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 short sentence generation, voice chat, online social scenarios with low latency, but text length limit is less than 10,000 characters. For long text, it is recommended to use Async 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, length limit less than 10,000 characters. Use newline characters for paragraph breaks. (To control pause duration in speech, add <#x#> between characters, where x is in seconds, supporting 0.01-99.99 with up to two decimal places). Supports custom time intervals between text segments to achieve custom speech pause durations. Note that text intervals must be set between two text segments that can be vocalized, and multiple consecutive time intervals cannot be set.

voice_setting · object · required

Show properties

speed · float · default: "1.0"

Range [0.5, 2], Default: 1.0

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

vol · float · default: "1.0"

Range (0, 10], Default: 1.0

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

pitch · int · 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. Either this or timbre_weights is required.

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"]

latex_read · bool · default: "false"

Controls whether to support reading LaTeX formulas. Default: false.

Notes:

1. Formulas in the request must be wrapped with $$ at the beginning and end;
2. If formulas contain "", they must be escaped as ”\”.

Example: The basic formula for derivatives is $$\\frac{d}{dx}(x^n) = nx^{n-1}$$

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 · int · default: "32000"

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

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

bitrate · int · 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 · int · 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.

timbre_weights · object[]

Either this or voice_id is required.

Show properties

voice_id · string

The voice ID for the request. Must be provided together with the weight parameter.

weight · int

Range [1, 100]

Weight, must be provided together with voice_id. Supports mixing up to 4 voices. Values must be integers; a higher proportion for a single voice results in a synthesized voice more similar to that voice.

stream · boolean · default: "false"

Whether to enable streaming. Default: false (streaming disabled).

stream_options · object

Show properties

exclude_aggregated_audio · boolean · default: "false"

When this parameter is set to True, the last chunk in streaming will not contain the concatenated complete audio hex data. Default: False, meaning the last chunk contains the concatenated complete audio hex data.

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'

output_format · string · default: "hex"

Parameter that controls the output format. Possible values: url, hex. Default: hex. This parameter only takes effect in non-streaming scenarios; streaming scenarios only support hex output. The returned URL is valid for 24 hours.

voice_modify · object

Voice effect settings. Supported audio formats for this parameter:

• Non-streaming: mp3, wav, flac
• Streaming: mp3

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

audio · string

The synthesized audio segment, hex-encoded, generated in the format defined by the input (audio_setting.format) (mp3/pcm/flac). The return format is determined by output_format; when stream is true, only hex format is supported.

status · number

Current audio stream status, only returned when stream is true. 1 indicates synthesis in progress, 2 indicates synthesis complete.