Reference
Remy Reference/models/Minimax Speech 2.8 HD
W

Minimax Speech 2.8 HD

Minimax Speech 2.8 HD, a text-to-speech model from WaveSpeed.
speechModelOverride: { model: "minimax-speech-2.8-hd" }
MiniMax·served viaWaveSpeed·Released January 2026
Pricing
List price
$0.007/run
Per generation
$0.00010
Specifications
Context window
50,000 tokens
Released
January 2026
Model string
minimax/speech-2.8-hd
Parameters
Model options, passed in speechModelOverride.config.
ParameterTypeDefaultRange / options
voice_id
Voice preset to use for speech synthesis.
SelectFriendly_PersonWise_WomanFriendly_PersonInspirational_girlDeep_Voice_ManCalm_WomanCasual_Guy+11
speed
Speech speed multiplier.
Number10.5–2, step 0.1
volume
Volume level.
Number10–2, step 0.1
pitch
Pitch adjustment.
Number0-12–12, step 1
emotion
Emotional tone of the speech delivery.
Selecthappysadangryfearfuldisgustedsurprised+1
sample_rate
Audio sample rate in Hz.
Select4410016000240003200044100
bitrate
Audio bitrate in bits per second.
Select1280003200064000128000256000
channel
Audio channel configuration.
Select12
format
Output audio format.
Selectmp3wavflacoggpcm
language_boost
Boost recognition for a specific language.
SelectautoAfrikaansArabicBulgarianCatalanChinese+35
english_normalization
Improves number-reading performance in English text (dates, currencies, etc.).
Booleanfalse
Voices · 17
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
Use this model
await mindstudio.textToSpeech({
  text: "...",
  speechModelOverride: {
    model: "minimax-speech-2.8-hd",
    config: {
      voice_id: "Wise_Woman",
      speed: 1,
    },
  },
});