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

# MiniMax Speech 2.8 HD Sync Text-to-Speech

MiniMax synchronous text-to-speech API using HTTP protocol. Supports various voice, emotion, speed and other parameter settings.

## Request Headers

**Content-Type** `string` *required*

Supports: `application/json`

**Authorization** `string` *required*

Bearer authentication format, for example: Bearer \{\{API Key}}.

## Request Body

**text** `string` *required*

Text to synthesize into speech, length limit is less than 10000 characters. If text length is greater than 3000 characters, streaming output is recommended. Supports paragraph breaks (newline), pause control (`<#x#>` tag), 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 is false

**voice\_modify** `object`

**properties**

**pitch** `integer`

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

Value range: \[-100, 100]

**timbre** `integer`

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

Value range: \[-100, 100]

**intensity** `integer`

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

Value range: \[-100, 100]

**sound\_effects** `string`

Sound effect setting, only one can be selected at a time. Options: spacious\_echo (spacious echo), auditorium\_echo (auditorium broadcast), lofi\_telephone (telephone distortion), robotic (electronic)

Optional values: `spacious_echo`, `auditorium_echo`, `lofi_telephone`, `robotic`

**audio\_setting** `object`

**properties**

**format** `string` (default: mp3)

Audio output format. wav is only supported in non-streaming output

Optional values: `mp3`, `pcm`, `flac`, `wav`

**bitrate** `integer` (default: 128000)

Audio bitrate. Options: \[32000, 64000, 128000, 256000], default is 128000. This parameter only applies to mp3 format

Optional values: `32000`, `64000`, `128000`, `256000`

**channel** `integer` (default: 1)

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

Optional values: `1`, `2`

**force\_cbr** `boolean` (default: false)

Controls constant bitrate (CBR) encoding. When set to true, audio will be encoded with constant bitrate. Note: This parameter only works when streaming output is enabled and audio format is mp3

**sample\_rate** `integer` (default: 32000)

Audio sample rate. Options: \[8000, 16000, 22050, 24000, 32000, 44100], default is 32000

Optional values: `8000`, `16000`, `22050`, `24000`, `32000`, `44100`

**output\_format** `string` (default: hex)

Controls output format, options are url or hex, default is hex. This parameter is only valid in non-streaming scenarios. URL is valid for 24 hours

Optional values: `url`, `hex`

**voice\_setting** `object`

**properties**

**vol** `number` (default: 1)

Audio volume, higher value means louder. Range (0, 10], default is 1.0

Value range: \[0, 10]

**pitch** `integer` (default: 0)

Audio pitch, range \[-12, 12], default is 0, where 0 is original voice output

Value range: \[-12, 12]

**speed** `number` (default: 1)

Speech speed, higher value means faster. Range \[0.5, 2], default is 1.0

Value range: \[0.5, 2]

**emotion** `string`

Controls the emotion of synthesized speech. Options correspond to 8 emotions: happy, sad, angry, fearful, disgusted, surprised, calm, fluent, whisper. The model will automatically match appropriate emotion based on input text

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

**voice\_id** `string` *required*

Voice ID for audio synthesis. If mixed voice is needed, set timber\_weights parameter and leave this empty. Supports system voice, cloned voice, and text-generated voice

**latex\_read** `boolean` (default: false)

Controls whether to read LaTeX formulas, default is false. Only supports Chinese. When enabled, language\_boost will be set to Chinese

**text\_normalization** `boolean` (default: false)

Whether to enable Chinese/English text normalization, which can improve performance in number reading scenarios but slightly increases latency. Default is false

**aigc\_watermark** `boolean` (default: false)

Controls whether to add audio rhythm identifier at the end of synthesized audio, default is false. This parameter is only valid for non-streaming synthesis

**language\_boost** `string`

Whether to enhance recognition ability for specified minor languages and dialects. Default is null, can be set to auto to let the model decide automatically

Optional 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`

**properties**

**exclude\_aggregated\_audio** `boolean` (default: false)

Sets whether the last chunk contains the concatenated audio hex data. Default is false, meaning the last chunk contains the complete concatenated audio hex data

**timber\_weights** `object[]`

Mixed voice settings, supports up to 4 voice mixtures

**properties**

**weight** `integer` *required*

Weight of each voice in the mix, must be set together with voice\_id. Range \[1, 100], supports up to 4 voice mixtures. Higher weight means more similarity to that voice

Value range: \[1, 100]

**voice\_id** `string` *required*

Voice ID for audio synthesis, must be set together with weight parameter. Supports system voice, cloned voice, and text-generated voice

**subtitle\_enable** `boolean` (default: false)

Controls whether to enable subtitle service, default is false. This parameter is only valid in non-streaming output scenarios, and only valid for speech-2.6-hd, speech-2.6-turbo, speech-01-turbo, speech-01-hd models

**pronunciation\_dict** `object`

**properties**

**tone** `string[]`

Defines pronunciation or replacement rules for special characters or symbols. For Chinese text, tones are represented by numbers: 1st tone = 1, 2nd tone = 2, 3rd tone = 3, 4th tone = 4, neutral tone = 5. Example: \["omg/oh my god"]

## Response

**data** `object`

Returned synthesis data object, may be null and needs null check

**properties**

**audio** `string`

Synthesized audio data in hex encoding, format matches the output format specified in request

**status** `integer`

Current audio stream status: 1 means synthesizing, 2 means synthesis completed

**subtitle\_file** `string`

Subtitle download link. Subtitles for the audio file, accurate to sentence (no more than 50 characters), in milliseconds, JSON format

**trace\_id** `string`

Session ID for this request, used for troubleshooting

**base\_resp** `object`

Status code and details for this request

**properties**

**status\_msg** `string`

Status details

**status\_code** `integer`

Status code. 0: success, 1000: unknown error, 1001: timeout, 1002: rate limit triggered, 1004: authentication failed, 1039: TPM rate limit triggered, 1042: invalid characters exceed 10%, 2013: invalid input parameters

**extra\_info** `object`

Additional audio information

**properties**

**bitrate** `integer`

Audio bitrate

**audio\_size** `integer`

Audio file size in bytes

**word\_count** `integer`

Word count of pronounced text, includes Chinese characters, numbers, letters, excludes punctuation

**audio\_format** `string`

Generated audio file format. Options: \[mp3, pcm, flac]

Optional values: `mp3`, `pcm`, `flac`

**audio\_length** `integer`

Audio duration in milliseconds

**audio\_channel** `integer`

Generated audio channel count, 1: mono, 2: stereo

**usage\_characters** `integer`

Billable character count

**audio\_sample\_rate** `integer`

Audio sample rate

**invisible\_character\_ratio** `number`

Invalid character ratio. If invalid characters do not exceed 10% (inclusive), audio will be generated normally with this ratio data returned; if exceeds 10%, an error will be returned


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.