Skip to content
Audio

Gemini Audio (TTS)

Gemini 3.1 Flash TTS, 2.5 Flash TTS, and 2.5 Pro TTS for text-to-speech. Generate natural speech directly on the canvas. BYO Gemini key.

What you can do

Generate speech from text with Gemini TTS models. The Audio node runs Gemini 3.1 Flash TTS (fastest), 2.5 Flash TTS, and 2.5 Pro TTS (highest quality). Select a model from the dropdown and pipe audio to the next node.

  • Gemini 3.1 Flash TTS, 2.5 Flash TTS, 2.5 Pro TTS
  • Fast synthesis with Flash models
  • Higher quality with Pro models
  • Audio output routed to downstream nodes
  • BYO Gemini API key, billed by Google at Gemini API rates

Generate your first video ad in 3 minutes.

Free to start. No credit card. Upload a product photo, connect your AI models, click Run.