ComfyUI Node
🔱 Gemini Speech
Generates speech from text using the Gemini TTS model.
🔱 Gemini Speech
- audio
◄text_promptA cat with a hat►
◄voiceKore►
◄api_key►
◄modelgemini-2.5-flash-preview-tts►
◄max_tokens5000►
◄temperature0.7►
CategoryArtha/LLM/GEMINI
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| text_prompt | STRING | A cat with a hat | — |
| voice | COMBO | Kore | 30 options: Zephyr, Autonoe, Puck, Laomedeia, Charon, Rasalgethi, +24 |
| api_key | STRING | API key will be visible in plain text. Consider adding your api to the api.json located inside this custom node folder. | |
| model | COMBO | gemini-2.5-flash-preview-tts | 1 options: gemini-2.5-flash-preview-tts |
| max_tokens | INT | 50001–8192 | For Gemini models, a token is equivalent to about 4 characters. 100 tokens is equal to about 60-80 English words. |
| temperature | FLOAT | 0.70–2 | A temperature of 0 means only the most likely tokens are selected, and there's no randomness. Conversely, a high temperature injects a high degree of randomness into the tokens selected by the model, leading to more unexpected, surprising model responses. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |