Audio Generation

Summary: XBRUSH's audio generation provides four features: text-to-speech (TTS), AI music composition, sound effects, and lip-sync. You can generate various types of audio content using text or video as input.

---

What is Audio Generation?

Audio generation is XBRUSH's feature for creating voice, music, sound effects, and lip-sync audio using AI. It supports four sub-features: TTS for reading text aloud, music composition in your desired genre, automatic background sound generation for videos, and lip-sync that combines an image with audio.

---

Audio Generation Overview

• In the Workspace input box, switch to Direct mode and select the Audio tab.
• An image, video, or audio file may be required depending on the feature.
• Four sub-tabs are available: Voice / Music / SFX / Lip Sync.
• Voice reads text aloud.
• Music composes a piece of music based on a text description.
• SFX generates sound effects that match an uploaded video (or from a text description).
• Lip Sync combines an uploaded image with voice audio to create a video with synchronized lip movements.
• Each sub-tab is a compact strip inside the input box: the prompt line (where the sub-tab takes one), the option chips, and a bottom row with Chat | Direct, "Generating starts a new session", Run · New line, and the action button with its credit cost.

Voice (Text To Speech)

Audio › Voice: the prompt line ("Enter text to convert to speech."), the Gemini engine chip, the voice chip 광고 보이스오버 1, and the Generate button.

• Converts text to speech.
• The default AI engine is Gemini, and the default voice is 광고 보이스오버 1 (a Korean-named voice, "ad voiceover 1"; the name stays in Korean even in the English UI). Click the voice chip to pick a different voice if you like. The available voices and options (such as filters or sliders) depend on the engine you select.
• Enter the text you want read aloud and click Generate. The credit cost is shown on the Generate button.

Music

Audio › Music: the prompt line ("Describe the music you want."), + Reference Image, the Lyria 3 engine chip, Settings, and the Generate button.

• Generates music.
• The AI engine is Lyria 3. You can optionally upload a Reference Image to guide the music, and Settings holds additional music options.
• Enter your desired genre, instruments, and mood as text, then generate.
• For example, entering "Compose a fingerstyle piece for classical guitar with a melody" will produce a guitar instrumental.

Sound Effects

Audio › SFX: From Video | From Text, + Source Video · required, the Pixverse Sound Effects engine chip, and the Generate button. The prompt line reads "Add more detail if needed."

• Generates sound effects. Choose From Video or From Text.
• In From Video mode, upload the video with + Source Video · required, add more detail if needed, then click Generate. The engine is Pixverse Sound Effects.
• The system creates sound effects that fit the uploaded video.

Lip-sync

Audio › Lip Sync: + Source Image · required, + Voice audio · required, the InfiniteTalk engine chip, 480p, and the Proceed button. There is no prompt line.

• Combines audio with an image to create a synchronized video.
• Upload an image with + Source Image · required and the voice with + Voice audio · required, then click Proceed to generate a lip-synced video. The AI engine is InfiniteTalk, and the resolution chip defaults to 480p (click it to choose another).
• The final output matches the length of the input audio.

Next Steps

1. Video Generation
2. Editor — Create presentations using images and videos
3. Social Media — Publish results to your social accounts