ComfyUI Node
MiniMax 音乐/语音/声音克隆（4 合 1）
A ComfyUI node in Seedance with 22 inputs and 6 outputs.
MiniMax 音乐/语音/声音克隆（4 合 1）
- reference_audio
- api_config
- audio
- audio_url
- audio_path
- result_text
- task_id
- response
◄modelminimax-speech-2.8-turbo►
◄prompt►
◄lyrics►
◄is_instrumentaltrue►
◄lyrics_optimizerfalse►
◄voice_idWise_Woman►
◄speed1.00►
◄volume1.0►
◄pitch0►
◄language_boostauto►
◄output_formatmp3►
◄sample_rate32000►
◄bitrate128000►
◄channel1►
◄custom_voice_idSeedanceVoice01►
◄clone_target_modelminimax-speech-2.8-hd►
◄need_noise_reductionfalse►
◄need_volume_normalizationfalse►
◄skip_errorfalse►
◄seed0►
CategorySeedance
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | minimax-speech-2.8-turbo | Choose music, HD/Turbo speech, or voice cloning. | 选择音乐、HD/Turbo 语音或声音克隆。 |
| prompt | STRING | Music style, speech text, or clone preview text according to the selected model. | 按模型填写音乐风格、朗读文本或克隆试听文本。 | |
| lyrics | STRING | Music only: lyrics with optional structure tags. | 仅音乐：歌词，可包含结构标签。 | |
| is_instrumental | BOOLEAN | true | Music only: generate without vocals; lyrics are then omitted. | 仅音乐：生成纯音乐，此时不提交歌词。 |
| lyrics_optimizer | BOOLEAN | false | Music only: generate lyrics from the prompt when lyrics are empty. | 仅音乐：歌词为空时根据提示词生成歌词。 |
| voice_id | STRING | Wise_Woman | Speech only: MiniMax system or cloned voice ID. | 仅语音：MiniMax 系统或克隆音色 ID。 |
| speed | FLOAT | 1.000.5–2 | Speech only: playback speed. | 仅语音：语速。 |
| volume | FLOAT | 1.00.1–10 | Speech only: volume. | 仅语音：音量。 |
| pitch | INT | 0-12–12 | Speech only: pitch adjustment. | 仅语音：音高调整。 |
| language_boost | COMBO | auto | Speech only: language recognition enhancement. | 仅语音：语言识别增强。 |
| output_format | COMBO | mp3 | Music/speech output format. | 音乐或语音输出格式。 |
| sample_rate | COMBO | 32000 | Music/speech output sample rate. | 音乐或语音输出采样率。 |
| bitrate | COMBO | 128000 | Music/speech output bitrate. | 音乐或语音输出码率。 |
| channel | COMBO | 1 | Speech only: mono or stereo. | 仅语音：单声道或双声道。 |
| custom_voice_id | STRING | SeedanceVoice01 | Voice Clone only: unique ID, 8-256 characters, starting with a letter. | 仅声音克隆：唯一 ID，8-256 字符且以字母开头。 |
| clone_target_model | COMBO | minimax-speech-2.8-hd | Voice Clone only: target speech model. | 仅声音克隆：目标语音模型。 |
| need_noise_reduction | BOOLEAN | false | Voice Clone only: reduce reference noise. | 仅声音克隆：降低参考音频噪声。 |
| need_volume_normalization | BOOLEAN | false | Voice Clone only: normalize reference volume. | 仅声音克隆：归一化参考音量。 |
| reference_audioopt | AUDIO | Voice Clone only: one 10-second to 5-minute reference audio. | 仅声音克隆：一段 10 秒到 5 分钟的参考音频。 | |
| api_configopt | SEEDANCE_CONFIG | Connect Seedance API Config; otherwise SEEDANCE_API_KEY is used. | |
| skip_erroropt | BOOLEAN | false | On failure return one second of silence instead of stopping the workflow. | 失败时输出 1 秒静音。 |
| seedopt | INT | 00–18446744073709550000 | ComfyUI cache seed. Fixed reuses the cached result while all other inputs stay unchanged; randomize/increment/decrement starts a new execution. This value is not sent to models without documented seed support. | ComfyUI 缓存种子；Fixed 在其他输入不变时复用缓存，随机、递增或递减会触发新任务。未声明支持 seed 的模型不会收到此参数。 |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |
| audio_url | STRING | — |
| audio_path | STRING | — |
| result_text | STRING | — |
| task_id | STRING | — |
| response | STRING | — |