Nodes/ComfyUI-JM-MiniMax-API/MiniMax Text to Speech
ComfyUI Node

MiniMax Text to Speech

A ComfyUI node in JM-MiniMax-API/Speech with 15 inputs and 3 outputs.

By juemingai·Created about a year ago·Updated 11 months ago· 5
MiniMax Text to Speech
    • audio_path
    • subtitle_path
    • audio_url
    api_key
    group_id
    text
    modelspeech-2.5-hd-preview
    voice_id
    speed1.0
    volume1.0
    pitch0
    emotion
    subtitle_enablefalse
    filename_prefixtts_output
    seed0
    custom_voice_id
    language_boostauto
    output_formathex
    CategoryJM-MiniMax-API/Speech

    Inputs (15)

    NameTypeDefaultDescription
    api_keySTRING
    group_idSTRING
    textSTRING
    modelCOMBOspeech-2.5-hd-preview5 options: speech-2.5-hd-preview, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo
    voice_idSTRING
    speedFLOAT1.00.5–2
    volumeFLOAT1.00.1–10
    pitchINT0-12–12
    emotionCOMBO8 options: , happy, sad, angry, fearful, disgusted, +2
    subtitle_enableBOOLEANfalse
    filename_prefixSTRINGtts_output
    seedINT00–18446744073709550000
    custom_voice_idoptSTRING
    language_boostoptCOMBOauto25 options: auto, Chinese, Chinese,Yue, English, Arabic, Russian, +19
    output_formatoptCOMBOhexhex: 返回十六进制编码的音频数据; url: 返回音频下载链接(有效期24小时)

    Outputs (3)

    NameTypeDescription
    audio_pathSTRING
    subtitle_pathSTRING
    audio_urlSTRING