MiniMax Speech-2.6-turbo Async Text-to-Speech

POST /v3/async/minimax-speech-2.6-turbo

MiniMax Speech-2.6-turbo Async Text-to-Speech

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/async/minimax-speech-2.6-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>",
    "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-2.6-turbo"

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-2.6-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/async/minimax-speech-2.6-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>',
        '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-2.6-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    \"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-2.6-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    \"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-2.6-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    \"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 async text-to-speech generation, with a maximum of 1 million characters per request. The complete audio result can be retrieved asynchronously. Supports 100+ system voices and cloned voices; supports pitch, speed, volume, bitrate, sample rate, and output format adjustments.

After submitting a long text speech synthesis request, please note that the returned URL is valid for 24 hours from the time it is returned. Please be mindful of the download timing.

Suitable for long text speech generation such as entire books; task queuing may take longer. For short sentence generation, voice chat, 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, maximum length 50,000 characters.

voice_setting · object · required

Show properties

speed · number

Range [0.5, 2], Default: 1.0

Speech speed of the generated voice. Optional; higher values produce faster speech.

vol · number

Range (0, 10], Default: 1.0

Volume of the generated voice. Optional; higher values produce louder audio.

pitch · number · default: 0

Range [-12, 12], Default: 0

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

voice_id · string

The voice ID for the request.

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

• Youthful Young Man: male-qn-qingse
• Elite Young Man: male-qn-jingying
• Assertive Young Man: male-qn-badao
• College Student: male-qn-daxuesheng
• Young Girl: female-shaonv
• Mature Lady: female-yujie
• Mature Woman: female-chengshu
• Sweet Woman: 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 Young Man (beta): male-qn-qingse-jingpin
• Elite Young Man (beta): male-qn-jingying-jingpin
• Assertive Young Man (beta): male-qn-badao-jingpin
• College Student (beta): male-qn-daxuesheng-jingpin
• Young Girl (beta): female-shaonv-jingpin
• Mature Lady (beta): female-yujie-jingpin
• Mature Woman (beta): female-chengshu-jingpin
• Sweet Woman (beta): female-tianmei-jingpin
• Clever Boy: clever_boy
• Cute Boy: cute_boy
• Lovely Girl: lovely_girl
• Cartoon Pig: cartoon_pig
• Clingy Brother: bingjiao_didi
• Handsome Boyfriend: junlang_nanyou
• Innocent Junior: chunzhen_xuedi
• Cool Senior: lengdan_xiongzhang
• Bossy Young Master: badao_shaoye
• Sweetheart Xiaoling: 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 may slightly increase latency. Default: false.

audio_setting · object

Show properties

sample_rate · number · default: 32000

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

Sample rate of the generated audio. Optional, Default: 32000.

bitrate · number · default: 128000

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

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

format · string · default: "mp3"

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

channel · number · default: 1

Number of audio channels. Default: 1 (mono). Options:

1: Mono

2: Stereo

pronunciation_dict · object

Show properties

tone · list

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

Pronunciation replacement (adjust tones / replace with other character pronunciations), format as follows:

["omg/oh my god"]

For Chinese text, 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 capability for 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: mp3, wav, flac

Show properties

pitch · integer

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

intensity · integer

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

timbre · integer

Timbre adjustment (resonant/crisp), Range [-100, 100]. Values closer to -100 produce a richer voice; values closer to 100 produce a crisper voice.

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.