MiniMax Speech 2.8 HD

The best-sounding of the lot, with feelings you pick rather than describe. Made by MiniMax. From $0.11 a 1,000 characters.

minimax-speech-2.8-hd

Get API key API reference Add funds

TypeVoice

InputsText

From$0.11 / 1K chars

UpdatedOct 12, 2026

Pricing

Setting	MiniAPI	fal	Difference
any	$0.11 / 1K chars	$0.10	+10%

Parameters

Name	Required	Values	Default	Description
prompt	Yes	text		What to make, in plain words.
language_boost	No	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, Slovak, Swedish, Croatian, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Afrikaans, auto		Enhance recognition of specified languages and dialects
output_format	No	url, hex	hex	File type of the result.
voice_setting	No			Voice configuration settings
audio_setting	No			Audio configuration settings
pronunciation_dict	No			Custom pronunciation dictionary for text replacement
normalization_setting	No			Loudness normalization settings for the audio
voice_modify	No			Voice modification settings to adjust pitch, intensity, and timbre.
audio_setting.bitrate	No	32000, 64000, 128000, 256000		Bitrate of generated audio
audio_setting.channel	No	1, 2		Number of audio channels (1=mono, 2=stereo)
audio_setting.format	No	mp3, pcm, flac		Audio format
audio_setting.sample_rate	No	8000, 16000, 22050, 24000, 32000, 44100		Sample rate of generated audio
normalization_setting.enabled	No			Enable loudness normalization for the audio
normalization_setting.target_loudness	No	-70 to -10		Target loudness in LUFS (default -18.0)
normalization_setting.target_peak	No	-3 to 0		Target peak level in dBTP (default -0.5).
normalization_setting.target_range	No	0 to 20		Target loudness range in LU (default 8.0)
pronunciation_dict.tone_list	No			List of pronunciation replacements in format ['text/(pronunciation)', ...]. For Chinese, tones are 1-5. Example: ['燕少飞/(yan4)(shao3)(fei1)']
voice_modify.intensity	No	-100 to 100		Intensity/energy of the voice. Range: -100 to 100. Higher values create more energetic speech.
voice_modify.pitch	No	-100 to 100		Pitch adjustment in semitones. Range: -100 to 100. Positive values raise pitch, negative values lower it.
voice_modify.timbre	No	-100 to 100		Timbre adjustment. Range: -100 to 100. Affects the tonal quality of the voice.
voice_setting.emotion	No	happy, sad, angry, fearful, disgusted, surprised, neutral		Emotion of the generated speech
voice_setting.english_normalization	No			Enables English text normalization to improve number reading performance, with a slight increase in latency
voice_setting.pitch	No	-12 to 12		Voice pitch (-12 to 12)
voice_setting.speed	No	0.5 to 2		Speech speed (0.5-2.0)
voice_setting.voice_id	No			Predefined voice ID to use for synthesis
voice_setting.vol	No	0.01 to 10		Volume (0-10)

Quickstart

curl -X POST "https://api.minicut.ai/v1/queue/minimax-speech-2.8-hd" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox runs through snow at dawn"}'

200 OK

{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/minimax-speech-2.8-hd/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/minimax-speech-2.8-hd/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/minimax-speech-2.8-hd/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.003850",
  "currency": "USD"
}