MiniMax Speech 2.8 HD (Replicate)

A ComfyUI node in Replicate Select/tts with 13 inputs and 1 output.

By Pharma-Lobby·Created about a month ago·Updated about a month ago· 0

◄text►

◄voice_idEnglish_Wiselady►

◄speed1.00►

◄volume1.00►

◄pitch0►

◄emotionauto►

◄english_normalizationfalse►

◄sample_rate32000►

◄bitrate128000►

◄audio_formatmp3►

◄channelmono►

◄subtitle_enablefalse►

◄language_boostNone►

CategoryReplicate Select/tts

Inputs (13)

Name	Type	Default	Description
text	STRING		Text to narrate (max 10,000 characters). Use markers like <#0.5#> to insert pauses in seconds.
voice_idopt	STRING	English_Wiselady	Voice to synthesize. Pick any MiniMax system voice (e.g. English_Wiselady, English_Deep-VoicedGentleman) or a voice_id returned by https://replicate.com/minimax/voice-cloning. See the full list of voi
speedopt	FLOAT	1.000.5–2	Speech speed multiplier (0.5–2.0). Lower is slower, higher is faster.
volumeopt	FLOAT	1.000–10	Relative loudness. 1.0 is default MiniMax gain. Range 0–10.
pitchopt	INT	0-12–12	Semitone offset applied to the voice (−12 to +12).
emotionopt	COMBO	auto	Desired delivery style. Use auto to let MiniMax choose, or pick a specific emotion.
english_normalizationopt	BOOLEAN	false	Improve number/date reading for English text (adds a small amount of latency).
sample_rateopt	COMBO	32000	Audio sample rate in Hz.
bitrateopt	COMBO	128000	MP3 bitrate in bits per second. Only used when audio_format is mp3.
audio_formatopt	COMBO	mp3	File format for the generated audio. Choose mp3 for general use, wav/flac for lossless, or pcm for raw bytes.
channelopt	COMBO	mono	mono for 1 channel (default), stereo for 2 channels.
subtitle_enableopt	BOOLEAN	false	Return MiniMax subtitle metadata with sentence timestamps (non-streaming only).
language_boostopt	COMBO	None	Optional language hint. Choose Automatic to let MiniMax detect the language, or pick a specific locale.

Name	Type	Description
audio	AUDIO	—