> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax Speech-2.6-turbo Async Speech Synthesis

This API supports asynchronous text-to-speech generation. A single text generation request supports up to 1 million characters for transmission, and the complete generated audio result can be retrieved asynchronously. It supports 100+ system voices and custom cloned voices, as well as independent adjustment of intonation, speed, volume, bitrate, sample rate, and output format.

After submitting a long-text speech synthesis request, note that the returned url is valid for 24 hours from the time the url is returned. Please download the information in time.

<Tip>This is suitable for speech generation of long texts such as entire books, and task queueing may take a relatively long time. For short sentence generation, voice chat, online social scenarios, and similar use cases, we recommend using [synchronous speech synthesis](/en/docs/models/reference-minimax-speech-2.6-turbo).</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="text" type="string" required={true}>
  The text to be synthesized, with a maximum length of 50,000 characters.
</ParamField>

<ParamField body="voice_setting" type="object" required={true}>
  <Expandable title="properties">
    <ParamField body="speed" type="number" default={1.0}>
      Range \[0.5,2], default value is 1.0

      The speed of the generated voice. Optional. The larger the value, the faster the speech.
    </ParamField>

    <ParamField body="vol" type="number" default={1.0}>
      Range (0,10], default value is 1.0

      The volume of the generated voice. Optional. The larger the value, the higher the volume.
    </ParamField>

    <ParamField body="pitch" type="number" default={0}>
      Range \[-12,12], default value is 0

      The intonation of the generated voice. Optional. (0 means output the original voice; the value must be an integer.)
    </ParamField>

    <ParamField body="voice_id" type="string">
      The requested voice ID.

      Two types are supported: system voices (id) and cloned voices (id). The system voices (ID) are as follows:

      * Shy Young Male Voice: `male-qn-qingse`
      * Elite Young Male Voice: `male-qn-jingying`
      * Dominant Young Male Voice: `male-qn-badao`
      * Young College Student Voice: `male-qn-daxuesheng`
      * Girl Voice: `female-shaonv`
      * Mature Lady Voice: `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`
      * Shy Young Male Voice-beta: `male-qn-qingse-jingpin`
      * Elite Young Male Voice-beta: `male-qn-jingying-jingpin`
      * Dominant Young Male Voice-beta: `male-qn-badao-jingpin`
      * Young College Student Voice-beta: `male-qn-daxuesheng-jingpin`
      * Girl Voice-beta: `female-shaonv-jingpin`
      * Mature Lady Voice-beta: `female-yujie-jingpin`
      * Mature Female Voice-beta: `female-chengshu-jingpin`
      * Sweet Female Voice-beta: `female-tianmei-jingpin`
      * Clever Boy: `clever_boy`
      * Cute Boy: `cute_boy`
      * Lovely Girl: `lovely_girl`
      * Cartoon Pig Xiaoqi: `cartoon_pig`
      * Yandere Younger Brother: `bingjiao_didi`
      * Handsome Boyfriend: `junlang_nanyou`
      * Innocent Junior Schoolmate: `chunzhen_xuedi`
      * Aloof Senior: `lengdan_xiongzhang`
      * Dominant Young Master: `badao_shaoye`
      * Sweetheart Xiaoling: `tianxin_xiaoling`
      * Playful Cute Girl: `qiaopi_mengmei`
      * Charming Mature Lady: `wumei_yujie`
      * Sweet Junior Schoolmate: `diadia_xuemei`
      * Elegant Senior Schoolmate: `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`
    </ParamField>

    <ParamField body="emotion" type="string">
      Controls the emotion of the synthesized speech;

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

      Parameter range: `["happy", "sad", "angry", "fearful", "disgusted", "surprised", "neutral"]`
    </ParamField>

    <ParamField body="text_normalization" type="bool" default="false">
      This parameter supports English text normalization, which can improve performance in digit-reading scenarios, but will slightly increase latency. If not provided, the default value is false.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="audio_setting" type="object">
  <Expandable title="properties">
    <ParamField body="sample_rate" type="number" default={32000}>
      Range \[8000, 16000, 22050, 24000, 32000, 44100]

      The sample rate of the generated voice. Optional, default is 32000.
    </ParamField>

    <ParamField body="bitrate" type="number" default={128000}>
      Range \[32000, 64000, 128000, 256000]

      The bitrate of the generated voice. Optional, default value is 128000. This parameter only takes effect for audio in mp3 format.
    </ParamField>

    <ParamField body="format" type="string" default="mp3">
      The generated audio format. Default is mp3. Options: `mp3`, `pcm`, `flac`, `wav`. wav is only supported for non-streaming output.
    </ParamField>

    <ParamField body="channel" type="number" default={1}>
      The number of channels of the generated audio. Default is 1: mono. Options:

      1: mono

      2: stereo
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="pronunciation_dict" type="object">
  <Expandable title="properties">
    <ParamField body="tone" type="list">
      Replace text, symbols, and corresponding pronunciations that require special annotation.

      Replace pronunciation (adjust tone/replace with pronunciations of other characters), in the following format:

      `["燕少飞/(yan4)(shao3)(fei1)","达菲/(da2)(fei1)"，"omg/oh my god"]`

      Tones are represented by numbers: first tone (yinping) is 1, second tone (yangping) is 2, third tone (shangsheng) is 3, fourth tone (qusheng) is 4, and neutral tone is 5.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="language_boost" type="string" default="null">
  Enhances recognition capability for specified low-resource languages and dialects. After setting this, voice performance can be improved in the specified low-resource language/dialect scenarios. If the low-resource language type is unclear, you can select "auto", and the model will determine the low-resource language type automatically. The following values are supported:

  `'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'`
</ParamField>

<ParamField body="voice_modify" type="object">
  Voice effects settings. Supported audio formats for this parameter: mp3, wav, flac

  <Expandable title="properties">
    <ParamField body="pitch" type="integer">
      Pitch adjustment (deep/bright), range \[-100,100]. Values closer to -100 make the voice deeper; values closer to 100 make the voice brighter.
    </ParamField>

    <ParamField body="intensity" type="integer">
      Intensity adjustment (powerful/soft), range \[-100,100]. Values closer to -100 make the voice stronger; values closer to 100 make the voice softer.
    </ParamField>

    <ParamField body="timbre" type="integer">
      Timbre adjustment (magnetic/crisp), range \[-100,100]. Values closer to -100 make the voice richer; values closer to 100 make the voice crisper.
    </ParamField>

    <ParamField body="sound_effects" type="string">
      Sound effect setting. Only one can be selected per request. Options:

      * `spacious_echo` (spacious echo)
      * `auditorium_echo` (auditorium broadcast)
      * `lofi_telephone` (telephone distortion)
      * `robotic` (electronic voice)
    </ParamField>
  </Expandable>
</ParamField>

## Response Parameters

<ResponseField name="task_id" type="string" required={true}>
  The task\_id of the asynchronous task. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to obtain the generated result.
</ResponseField>