Audio nodes

Audio nodes cover voice and sound: text to speech, multi-speaker dialogue, music, digital avatars, voice cloning, and audio tools that work with video.

Voice generation (TTS)

Open Audio in the Add node menu to create Voice, Dialogue, Music and Digital Avatar nodes (entries with no available model are hidden). A voice generation node:

• Enter the text to read, pick a voice and parameters, and generate speech;
• The speed, pitch and volume sliders and the pause, tone and emotion markup buttons only appear when the selected model supports them;
• The text length limit depends on the selected model.

Voice cloning and design

• The voice picker has Voice library, My voices and Favorites;
• Clone voice: read a sample script aloud in the browser (about 10–20 seconds) to register a voice of your own, tied to the model you picked, and use it for speech;
• Voice design: design a new voice from a description, with no reference audio;
• Whether there is a fee depends on the model: some charge a registration fee at creation, some charge on the first synthesis, some are free. Registration finishes in the background; a voice can be picked once it moves from Registering to Ready. Voices left unused for a long time are cleaned up automatically.

Audio-related tools

Many audio abilities actually live on the video node toolbar (see Video nodes): split audio and video, audio mix, vocal separation and more can pull the sound out or replace it, and most are free.