Enterprise AI Resource Hub - 302.AI | Pay-as-you-go, Comprehensive AI model API Access, Instant Online App Usage

speech-2.8-hd

High-performance text-to-speech model launched by MiniMax

2026-02-06

Audio-Video Processing

Pricing:

$52.5/1M characters

starting from

Bulk order? Contact your manager for exclusive deals

稳定性

Stable

API Overview

MiniMax Speech 2.8 HD is MiniMax’s flagship text-to-speech product, positioned as a professional voice synthesis API that delivers studio-grade, high-fidelity audio quality. It meets the demands of high-end audio production with unparalleled clarity and naturalness.

Key Upgrades: Supports over 17 preset voices and custom clone voices; natively parses onomatopoeic expressions such as (laughs) and (sighs); and offers emotional control and pronunciation customization capabilities.
Applicable Scenarios: Professional audio applications including audiobook production, film and TV dubbing, podcast broadcasting, educational materials, accessibility services, and voice acting for video game characters.
Product Value: Allows fine-tuned adjustments to speed, pitch, volume, sampling rate, bit rate, and channel configuration, delivering ready-to-use, broadcast-quality audio.
Audio Quality Advantage: HD processing provides richer, cleaner audio details, with significantly improved naturalness compared to the Turbo version.
Technical Features: Supports English number normalization (english_normalization) and pronunciation dictionaries (pronunciation_dict), ensuring accurate pronunciation of brand names and technical terms.

───────────────────────────────────────────────────────────────────

Core Capabilities

🎙️ Studio-Grade Audio Quality

HD rendering delivers higher clarity and naturalness, ideal for final deliverables.

💬 Onomatopoeia Support

Natively recognizes 22 types of onomatopoeic expressions, including (laughs), (coughs), (gasps), and (sighs), enhancing the vividness of speech.

😊 Emotional Tone Control

Allows specifying emotion modes such as happy or calm to match the emotional tone of the content.

🎛️ Full Parameter Fine-Tuning

Enables free adjustment of speed, pitch, volume, as well as audio format, sample rate, bit rate, and channel.

🔤 Accurate Pronunciation Management

Uses pronunciation_dict to define the correct pronunciation of proper nouns and enables english_normalization to optimize the reading of English numbers and dates.

API Console

API Analytics

API Reference (4)

API Description	API Endpoint	Request Method	Stability	Parameter Description
T2A（Speech Generation - Synchronous）	https://api.302.ai/minimaxi/v1/t2a_v2	POST	Stable	View Details
Document Details Text-to-Speech Tone Frequency from Minimax Official documentation: https://platform.minimaxi.com/docs/api-reference/speech-t2a-http Voice list: https://platform.minimaxi.com/docs/faq/system-voice-id Pricing: Turbo version 30 PTC / million words Pricing: HD version 52.5 PTC / million words Request Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Content-Typestring Optional Example Value:`application/json` Request Body application/json modelenum<string> Required Requested model version, optional range：speech-2.8-turbo，speech-2.8-hd，speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo Enum Value: `speech-2.6-hdspeech-2.6-turbospeech-02-hdspeech-02-turbospeech-01-hdspeech-01-turbospeech-2.8-turbospeech-2.8-hd` textstring Required The text to be synthesized must be less than 10,000 characters in length. If the text exceeds 3,000 characters, it is recommended to use streaming output. streamboolean Optional Controls whether to enable streaming output. Default is false, which means streaming is not enabled. stream_optionsobject Optional exclude_aggregated_audioboolean Optional Set whether the last chunk contains the concatenated speech hex data. The default value is False. voice_settingobject Optional voice_idstring Optional The timbre number for synthesized audio, supports system timbres, recreated timbres, and text-to-sound timbres. speednumber Optional The speech rate of the synthesized audio, value range [0.5, 2], default value is 1.0 volnumber Optional The volume of the synthesized audio, value range (0,10], default value is 1.0 pitchinteger Optional The intonation of the synthesized audio, value range [-12,12], default value is 0 emotionenum<string> Optional Control the emotion of synthesized speech. The model will automatically match the emotion based on the input text. Enum Value: `happysadangryfearfuldisgustedsurprisedcalmfluent` text_normalizationboolean Optional Whether to enable Chinese and English text normalization. Enabling this option can improve performance in digital reading scenarios. latex_readboolean Optional Controls whether to read aloud latex formulas. The default is false. audio_settingobject Optional sample_rateenum<integer> Optional The sampling rate for generated audio, default is 32000. Enum Value: `80001600022050240003200044100` bitrateenum<integer> Optional The bitrate for generating audio, with a default value of 128000, is only applicable to the mp3 format. Enum Value: `3200064000128000256000` formatenum<string> Optional The format for generating audio, defaults to mp3. Enum Value: `mp3pcmflacwav` channelenum<integer> Optional Number of audio channels to generate: 1 for mono, 2 for stereo Enum Value: `12` force_cbrboolean Optional Whether to use constant bitrate encoding; only effective for streaming output and when the format is mp3. pronunciation_dictobject Optional tonearray[string] Optional Replacement rules for substituting special annotations, phonetic symbols, or pronunciation timber_weightsarray[object] Optional voice_idstring Optional Timbre number of synthesized audio weightinteger Optional The weight of the timbre, with a value range of [1, 100] language_boostenum<string> Optional Whether to enhance recognition capabilities for specified minority languages and dialects. The default value is null. Enum Value: `ChineseChinese,YueEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalianKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalayPersianSlovakSwedishCroatianFilipinoHungarianNorwegianSlovenianCatalanNynorskTamilAfrikaansauto` voice_modifyobject Optional pitchenum<integer> Optional Pitch adjustment (deep/bright), range [-100,100] Enum Value: `-100100` intensityenum<integer> Optional Intensity adjustment (strength/softness), range [-100,100] Enum Value: `-100100` timbreenum<integer> Optional Tone adjustment (magnetic/crisp), range [-100,100] Enum Value: `-100100` sound_effectsenum<string> Optional Sound Effect Settings Enum Value: `spacious_echoauditorium_echolofi_telephonerobotic` subtitle_enableboolean Optional Controls whether to enable the subtitle service; only effective for non-streaming output. output_formatenum<string> Optional Control the format of the output result. In streaming scenarios, only hex format is supported. Enum Value: `urlhex` aigc_watermarkboolean Optional Controls whether to add an audio rhythm marker at the end of the synthesized audio. The default value is False.
T2A（Async extra content generation）	https://api.302.ai/minimaxi/v1/t2a_async_v2	POST	Stable	View Details
Document Details Text-to-Audio Tone Frequency from Minimax Official documentation: https://platform.minimaxi.com/docs/guides/speech-t2a-async Voice list: https://platform.minimaxi.com/docs/faq/system-voice-id Pricing: Turbo version 30 PTC / million characters Pricing: HD version 52.5 PTC / million characters Request Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Content-Typestring Optional Example Value:`application/json` Request Body application/json modelenum<string> Required Requested model version, optional range：speech-2.8-turbo，speech-2.8-hd，speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo Enum Value: `speech-2.6-hdspeech-2.6-turbospeech-02-hdspeech-02-turbospeech-01-hdspeech-01-turbospeech-2.8-turbospeech-2.8-hd` textstring Required Text to be synthesized must be less than 50,000 characters in length, suitable for long text synthesis. voice_settingobject Optional voice_idstring Optional The timbre number for synthesized audio, supports system timbres, replicated timbres, and text-to-timbre. speednumber Optional The speech rate of the synthesized audio, value range [0.5, 2], default value is 1.0 volnumber Optional The volume of the synthesized audio, value range (0,10], default value is 1.0 pitchinteger Optional The intonation of the synthesized audio, value range [-12,12], default value is 0 emotionenum<string> Optional Control the emotion of synthesized speech; the model will automatically match the emotion based on the input text. Enum Value: `happysadangryfearfuldisgustedsurprisedcalmfluent` text_normalizationboolean Optional Whether to enable Chinese and English text normalization. Enabling this option can improve performance in digital reading scenarios. latex_readboolean Optional Controls whether to read aloud latex formulas. The default is false. audio_settingobject Optional sample_rateenum<integer> Optional The sampling rate for generated audio, default is 32000 Enum Value: `80001600022050240003200044100` bitrateenum<integer> Optional The bitrate for generating audio, with a default value of 128000, is only effective for the mp3 format. Enum Value: `3200064000128000256000` formatenum<string> Optional The format for generating audio is mp3 by default. Enum Value: `mp3pcmflacwav` channelenum<integer> Optional Number of audio channels to generate; 1 for mono, 2 for stereo Enum Value: `12` force_cbrboolean Optional Whether to use constant bitrate encoding; only effective for streaming output and when the format is mp3. pronunciation_dictobject Optional tonearray[string] Optional Replacement rules for substituting special annotated text or symbols with corresponding phonetic notation or pronunciation timber_weightsarray[object] Optional voice_idstring Optional Timbre number of the synthesized audio weightinteger Optional The weight of the timbre, value range [1, 100] language_boostenum<string> Optional Whether to enhance the recognition capability for specified minor languages and dialects. The default value is null. Enum Value: `ChineseChinese,YueEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalianKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalayPersianSlovakSwedishCroatianFilipinoHungarianNorwegianSlovenianCatalanNynorskTamilAfrikaansauto` voice_modifyobject Optional pitchenum<integer> Optional Pitch adjustment (deep/bright), range [-100,100] Enum Value: `-100100` intensityenum<integer> Optional Intensity Adjustment (Strength/Softness), range [-100,100] Enum Value: `-100100` timbreenum<integer> Optional Timbre adjustment (magnetic/crisp), range [-100,100] Enum Value: `-100100` sound_effectsenum<string> Optional Sound Effect Settings Enum Value: `spacious_echoauditorium_echolofi_telephonerobotic` output_formatenum<string> Optional Control the format of the output result; in streaming scenarios, only hex format is supported. Enum Value: `urlhex`
T2A（Status Inquiry）	https://api.302.ai/minimaxi/v1/query/t2a_async_query_v2	GET	Stable	View Details
Document Details Vincennes Tone Frequency from Minimax， Query Task Status Minimax：https://platform.minimaxi.com/document/T2A Large v2?key=66b3559f290299a26b2347d2 Price：0 PTC / call Request Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Content-Typestring Optional Example Value:`application/json` Query Parameters task_idstring Optional
Files（Audio File Download）	https://api.302.ai/minimaxi/v1/files/retrieve	GET	Stable	View Details
Document Details Vincennes Video Model from Minimax Minimax：https://platform.minimaxi.com/document/video_generation?key=66d1439376e52fcee2853049#whYrra7nHOP2eZy9yMMbnnU6 Price：0 PTC / call Request Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Query Parameters file_idstring Optional

API Pricing

$￥円 ₽

Model	Description	302.AI Price

speech-2.8-hd	T2A (voice generation-synchronization)	$52.5/1M characters
speech-2.8-hd	Asynchronous Long-form Text-to-Speech Generation	$52.5/1M characters
T2A	Status Inquiry	Free
Files（Audio File Download）	-	Free

speech-2.8-hd

API Overview

Core Capabilities

API Console

API Analytics

API Reference (4)

Header Parameters

Request Body application/json

Header Parameters

Request Body application/json

Header Parameters

Query Parameters

Header Parameters

Query Parameters

API Pricing

speech-2.8-hd

$52.5/1M characters

speech-2.8-hd

$52.5/1M characters

T2A

Free

Files（Audio File Download）

Free

Recommended

Quick Access

Support

Legal Statement