ComfyUI Node
Gemini 2.5 Pro TTS · Text to Speech
Directable voices for narration and two-person dialogue 0.07 credits ($0.0007) per second. Model: google/gemini-2.5-pro-tts/text-to-speech Fields, prices and examples: https://popnow.ai/docs/models/gemini-2-5-pro-tts
Gemini 2.5 Pro TTS · Text to Speech
- audio
- task id
◄text►
◄dialogue►
◄speakers►
◄voice_idKore►
◄stylemodel default►
◄pacemodel default►
◄accentneutral►
◄instructions►
◄scene►
◄temperature-1.00►
CategoryPopNow/Audio/Google
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | The words to be spoken, exactly as written. Cues in square brackets such as [sighs] are performed rather than read aloud. | |
| dialogue | STRING | A scripted conversation, used instead of text: each line names a speaker from speakers. JSON. A list of objects with "text", "speaker". | |
| speakers | STRING | The cast for dialogue: one or two voices, each with a name the lines refer to. JSON. A list of objects with "name", "pace"?, "style"?, "accent"?, "profile"?, "voice_id". | |
| voice_id | COMBO | Kore | Prebuilt voice that reads the text. Each voice has a fixed character. |
| style | COMBO | model default | Overall manner of the reading. Omit it to use the voice's own default manner. |
| pace | COMBO | model default | Rhythm of the reading. Omit it to keep the voice's own rhythm. |
| accent | COMBO | neutral | English accent used for the reading. |
| instructions | STRING | How to read the text: pace, mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken. | |
| scene | STRING | Where and to whom the words are spoken. Shapes the delivery and is not spoken. | |
| temperature | FLOAT | -1.00-1–2 | Variation between takes; higher is less predictable. -1 leaves it to the model. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | Several results come back as a batch; Save Audio writes one file each. |
| task id | STRING | The PopNow task id, for the API console logs or support. |