ComfyUI Node
Gemini TTS Multi API
This node uses the Google Gemini TTS API to generate multi-speaker speech from text.
Gemini TTS Multi API
- speaker_options
- config_options
- proxy_options
- AUDIO
- STRING
◄text## THE SCENE
设置场景的背景信息，包括地点、氛围和环境细节，以确定基调和氛围。
## DIRECTOR'S NOTES
导演备注,仅定义对性能至关重要的内容，并注意不要过度指定。最常见的指令是风格、语速和口音，但模型不限于这些指令，也不要求使用这些指令。您可以随意添加自定义说明
## TRANSCRIPT
转写内容和音频标记,转写内容是模型将要朗读的确切字词。音频标记是指方括号中的字词，用于指示说话方式、音调变化或插话。多说话人名称需要与配置对应，示例如下：
Speaker 1: I know right, I couldn't believe it. [whispers] She should have totally left at that point.
Speaker 2: [cough] Well, [sighs] I guess it doesn't matter now.►
◄modelgemini-2.5-flash-preview-tts►
◄seed0►
CategoryYCYY/API/audio
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | ## THE SCENE 设置场景的背景信息，包括地点、氛围和环境细节，以确定基调和氛围。 ## DIRECTOR'S NOTES 导演备注,仅定义对性能至关重要的内容，并注意不要过度指定。最常见的指令是风格、语速和口音，但模型不限于这些指令，也不要求使用这些指令。您可以随意添加自定义说明 ## TRANSCRIPT 转写内容和音频标记,转写内容是模型将要朗读的确切字词。音频标记是指方括号中的字词，用于指示说话方式、音调变化或插话。多说话人名称需要与配置对应，示例如下： Speaker 1: I know right, I couldn't believe it. [whispers] She should have totally left at that point. Speaker 2: [cough] Well, [sighs] I guess it doesn't matter now. | Conversation text. Include speaker labels that match the configured speaker names. |
| speaker_options | * | Speaker option array from Gemini Speaker Options or Gemini Batch Speakers Options | |
| model | COMBO | gemini-2.5-flash-preview-tts | 1 options: gemini-2.5-flash-preview-tts |
| seed | INT | 00–18446744073709550000 | — |
| config_optionsopt | * | Optional configuration override from YCYY Gemini TTS Config Options | |
| proxy_optionsopt | * | Optional proxy configuration override from YCYY Proxy Config Options |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| AUDIO | AUDIO | — |
| STRING | STRING | — |