MiniMax Speech 2.8 Turbo Sync Text-to-Speech

POST /v3/minimax-speech-2.8-turbo

MiniMax Speech 2.8 Turbo Sync Text-to-Speech

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/minimax-speech-2.8-turbo \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "text": "<string>",
  "stream": true,
  "voice_modify": {
    "pitch": 123,
    "timbre": 123,
    "intensity": 123,
    "sound_effects": "<string>"
  },
  "audio_setting": {
    "format": "<string>",
    "bitrate": 123,
    "channel": 123,
    "force_cbr": true,
    "sample_rate": 123
  },
  "output_format": "<string>",
  "voice_setting": {
    "vol": 123,
    "pitch": 123,
    "speed": 123,
    "emotion": "<string>",
    "voice_id": "<string>",
    "latex_read": true,
    "text_normalization": true
  },
  "aigc_watermark": true,
  "language_boost": "<string>",
  "stream_options": {
    "exclude_aggregated_audio": true
  },
  "timber_weights": [
    {
      "weight": 123,
      "voice_id": "<string>"
    }
  ],
  "subtitle_enable": true,
  "continuous_sound": true,
  "pronunciation_dict": {
    "tone": [
      {}
    ]
  }
}
'

import requests

url = "https://api.myrouter.ai/v3/minimax-speech-2.8-turbo"

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

fetch('https://api.myrouter.ai/v3/minimax-speech-2.8-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-2.8-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>',
    'stream' => true,
    'voice_modify' => [
        'pitch' => 123,
        'timbre' => 123,
        'intensity' => 123,
        'sound_effects' => '<string>'
    ],
    'audio_setting' => [
        'format' => '<string>',
        'bitrate' => 123,
        'channel' => 123,
        'force_cbr' => true,
        'sample_rate' => 123
    ],
    'output_format' => '<string>',
    'voice_setting' => [
        'vol' => 123,
        'pitch' => 123,
        'speed' => 123,
        'emotion' => '<string>',
        'voice_id' => '<string>',
        'latex_read' => true,
        'text_normalization' => true
    ],
    'aigc_watermark' => true,
    'language_boost' => '<string>',
    'stream_options' => [
        'exclude_aggregated_audio' => true
    ],
    'timber_weights' => [
        [
                'weight' => 123,
                'voice_id' => '<string>'
        ]
    ],
    'subtitle_enable' => true,
    'continuous_sound' => true,
    'pronunciation_dict' => [
        'tone' => [
                [
                                
                ]
        ]
    ]
  ]),
  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-2.8-turbo"

	payload := strings.NewReader("{\n  \"text\": \"<string>\",\n  \"stream\": true,\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"timbre\": 123,\n    \"intensity\": 123,\n    \"sound_effects\": \"<string>\"\n  },\n  \"audio_setting\": {\n    \"format\": \"<string>\",\n    \"bitrate\": 123,\n    \"channel\": 123,\n    \"force_cbr\": true,\n    \"sample_rate\": 123\n  },\n  \"output_format\": \"<string>\",\n  \"voice_setting\": {\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"speed\": 123,\n    \"emotion\": \"<string>\",\n    \"voice_id\": \"<string>\",\n    \"latex_read\": true,\n    \"text_normalization\": true\n  },\n  \"aigc_watermark\": true,\n  \"language_boost\": \"<string>\",\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"timber_weights\": [\n    {\n      \"weight\": 123,\n      \"voice_id\": \"<string>\"\n    }\n  ],\n  \"subtitle_enable\": true,\n  \"continuous_sound\": true,\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\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-2.8-turbo")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"text\": \"<string>\",\n  \"stream\": true,\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"timbre\": 123,\n    \"intensity\": 123,\n    \"sound_effects\": \"<string>\"\n  },\n  \"audio_setting\": {\n    \"format\": \"<string>\",\n    \"bitrate\": 123,\n    \"channel\": 123,\n    \"force_cbr\": true,\n    \"sample_rate\": 123\n  },\n  \"output_format\": \"<string>\",\n  \"voice_setting\": {\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"speed\": 123,\n    \"emotion\": \"<string>\",\n    \"voice_id\": \"<string>\",\n    \"latex_read\": true,\n    \"text_normalization\": true\n  },\n  \"aigc_watermark\": true,\n  \"language_boost\": \"<string>\",\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"timber_weights\": [\n    {\n      \"weight\": 123,\n      \"voice_id\": \"<string>\"\n    }\n  ],\n  \"subtitle_enable\": true,\n  \"continuous_sound\": true,\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.myrouter.ai/v3/minimax-speech-2.8-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  \"stream\": true,\n  \"voice_modify\": {\n    \"pitch\": 123,\n    \"timbre\": 123,\n    \"intensity\": 123,\n    \"sound_effects\": \"<string>\"\n  },\n  \"audio_setting\": {\n    \"format\": \"<string>\",\n    \"bitrate\": 123,\n    \"channel\": 123,\n    \"force_cbr\": true,\n    \"sample_rate\": 123\n  },\n  \"output_format\": \"<string>\",\n  \"voice_setting\": {\n    \"vol\": 123,\n    \"pitch\": 123,\n    \"speed\": 123,\n    \"emotion\": \"<string>\",\n    \"voice_id\": \"<string>\",\n    \"latex_read\": true,\n    \"text_normalization\": true\n  },\n  \"aigc_watermark\": true,\n  \"language_boost\": \"<string>\",\n  \"stream_options\": {\n    \"exclude_aggregated_audio\": true\n  },\n  \"timber_weights\": [\n    {\n      \"weight\": 123,\n      \"voice_id\": \"<string>\"\n    }\n  ],\n  \"subtitle_enable\": true,\n  \"continuous_sound\": true,\n  \"pronunciation_dict\": {\n    \"tone\": [\n      {}\n    ]\n  }\n}"

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

200

{
  "data": {},
  "trace_id": "<string>",
  "base_resp": {},
  "extra_info": {}
}

Convert text to speech with support for multiple voices, emotion control, speed adjustment, and more. Text length limit is less than 10,000 characters. For text longer than 3,000 characters, streaming output is recommended.

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 into speech. Length limit is less than 10,000 characters. For text longer than 3,000 characters, streaming output is recommended. Supports paragraph breaks (newline characters), pause control (<#x#> markers), and interjection tags (such as (laughs), (coughs), etc., only supported by speech-2.8-hd/turbo).

stream · boolean · default: false

Controls whether to enable streaming output. Default: false (streaming disabled).

voice_modify · object

Hide 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.

Range: [-100, 100]

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.

Range: [-100, 100]

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.

Range: [-100, 100]

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).

Possible values: spacious_echo, auditorium_echo, lofi_telephone, robotic

audio_setting · object

Hide properties

format · string · default: "mp3"

The format of the generated audio. wav is only supported in non-streaming output.

Possible values: mp3, pcm, flac, wav

bitrate · integer · default: 128000

The bitrate of the generated audio. Options: [32000, 64000, 128000, 256000], Default: 128000. This parameter only applies to mp3 format audio.

Possible values: 32000, 64000, 128000, 256000

channel · integer · default: 1

The number of audio channels. Options: [1, 2], where 1 is mono and 2 is stereo. Default: 1

Possible values: 1, 2

force_cbr · boolean · default: false

Controls constant bitrate (CBR) encoding for audio. When set to true, audio will be encoded at a constant bitrate. Note: This parameter only takes effect when streaming output is enabled and the audio format is mp3.

sample_rate · integer · default: 32000

The sample rate of the generated audio. Options: [8000, 16000, 22050, 24000, 32000, 44100], Default: 32000

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

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.

Possible values: url, hex

voice_setting · object

Hide properties

vol · number · default: 1

The volume of the synthesized audio. Higher values result in louder volume. Range (0, 10], Default: 1.0

Range: [0, 10]

pitch · integer · default: 0

The pitch of the synthesized audio. Range [-12, 12], Default: 0, where 0 outputs the original voice.

Range: [-12, 12]

speed · number · default: 1

The speech rate of the synthesized audio. Higher values result in faster speech. Range [0.5, 2], Default: 1.0

Range: [0.5, 2]

emotion · string

Controls the emotion of the synthesized speech. Corresponds to 9 emotions: happy, sad, angry, fearful, disgusted, surprised, neutral (calm), vivid (fluent), whisper. The model automatically matches appropriate emotions based on input text; manual specification is generally unnecessary.

Possible values: happy, sad, angry, fearful, disgusted, surprised, calm, fluent, whisper

voice_id · string · required

The voice ID for the synthesized audio. To set mixed voices, use the timber_weights parameter and set this parameter to an empty value. Supports system voices, cloned voices, and text-generated voices.

latex_read · boolean · default: false

Controls whether to read LaTeX formulas aloud. Default: false. Only supports Chinese; when enabled, the language_boost parameter will be set to Chinese.

text_normalization · boolean · default: false

Enables Chinese and English text normalization. When enabled, it can improve performance in number reading scenarios but slightly increases latency. Default: false.

aigc_watermark · boolean · default: false

Controls whether to add an audio rhythm identifier at the end of the synthesized audio. Default: false. This parameter only applies to non-streaming synthesis.

language_boost · string

Whether to enhance recognition of specified minority languages and dialects. Default: null. Can be set to auto to let the model automatically determine the language type.

Possible 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

stream_options · object

Hide properties

exclude_aggregated_audio · boolean · default: false

Controls whether the last chunk includes the concatenated speech hex data. Default: false, meaning the last chunk contains the complete concatenated speech hex data.

timber_weights · array

Mixed voice settings. Supports mixing up to 4 voices.

Hide properties

weight · integer · required

The weight of each voice in the synthesized audio. Must be provided together with voice_id. Range: [1, 100]. Supports mixing up to 4 voices. A higher proportion for a single voice results in greater similarity to that voice.

Range: [1, 100]

voice_id · string · required

The voice ID for the synthesized audio. Must be provided together with the weight parameter. Supports system voices, cloned voices, and text-generated voices.

subtitle_enable · boolean · default: false

Controls whether to enable the subtitle service. Default: false. This parameter is only effective in non-streaming output scenarios and only applies to speech-2.6-hd, speech-2.6-turbo, speech-02-turbo, speech-02-hd, speech-01-turbo, speech-01-hd models.

continuous_sound · boolean · default: false

Enable this parameter to make clause transitions more natural. Only supported for speech-2.8-hd and speech-2.8-turbo models.

pronunciation_dict · object

Hide properties

tone · array

Define pronunciation annotation or replacement rules for characters or symbols that require special marking. In Chinese text, tones are represented by numbers: 1st tone is 1, 2nd tone is 2, 3rd tone is 3, 4th tone is 4, neutral tone is 5. Example: [“omg/oh my god”]

Response

data · object

The returned synthesis data object. May be null; null-check is required.

trace_id · string

The session ID for this request, used to help locate issues during inquiries or feedback.

base_resp · object

The status code and details of this request.

extra_info · object

Additional information about the audio.