Skip to content
Start free

Text to speechEvery planfastbudgetvoice-clone-compatible

MiniMax Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo: a text to speech model you can use in AutoReel.

At a glance

Category
Text to speech
Produces
audio
Typical run time
~5 s
Plans
Every plan, including Free
Price
Depends on the settings; shown before you generate

Parameters

The settings MiniMax Speech 2.8 Turbo accepts. In the Studio they appear as a form with sensible defaults; through the API they’re the params of a generation.

textstringrequired
Text to convert to speech. Every character is 1 token. Maximum 10000 characters. Use <#x#> between words to control pause duration (0.01-99.99s).
pronunciation_dictlist of string
Format: Alias/Pronunciation, e.g. Omg/Oh my godUp to 100 items
voice_idstringrequired
Desired voice ID. Use a voice ID you have trained (https://wavespeed.ai/models/minimax/voice-clone), or one of the following system voice IDs: Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl.
speednumber
Speech speed. Range: 0.5-2.0, where 1.0 is normal speed.Range: 0.5 to 2Default: 1
volumenumber
Speech volume. Range: 0.1-10.0, where 1.0 is normal volume.Range: 0.1 to 10Default: 1
pitchnumber
Speech pitch. Range: -12 to 12, where 0 is normal pitch.Range: -12 to 12Default: 0
emotionchoice
The emotion of the generated speech.One of: happy, sad, angry, fearful, disgusted, surprised, neutralDefault: happy
english_normalizationboolean
This parameter supports English text normalization, which improves performance in number-reading scenarios.Default: false
sample_ratechoice
Sample rate of generated sound.One of: 8000, 16000, 22050, 24000, 32000, 44100
bitratechoice
Bitrate of generated sound.One of: 32000, 64000, 128000, 256000
channelchoice
The number of channels of the generated audio. 1: mono, 2: stereo.One of: 1, 2
formatchoice
Format of generated sound.One of: mp3, wav, pcm, flac
language_boostchoice
Enhance the ability to recognize specified languages and dialects.One of: 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
enable_base64_outputboolean
If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.Default: false
enable_sync_modeboolean
If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.Default: false

models

Make your first reel free

Sign up and get 100 credits to try every format: AI UGC videos, talking creators, slideshows and hook + demo reels. No card needed.

Start freeSee pricing