Skip to main content

How to generate Audio on Layer

Create everything from character VO to sound effects for game scenes with Audio for game production.

Updated over 2 weeks ago

Layer now supports audio generation powered by ElevenLabs, enabling you to create both voiceovers and sound effects directly in your creative workflow - as well as lipsync audio in videos.

Whether you’re building a game, animating a character, or creating rich in-world audio for a video, our audio tools are designed to help you bring your characters and scenes to life with high-quality, emotionally expressive sound.


Voice Generation

Voice generation is powered by ElevenLabs’ multilingual v2 model, known for its high emotional range, contextual awareness, and lifelike speech.

Key Features

  • 10 Character Voices Available
    Choose from a curated set of expressive voices for your game or video characters.

  • Multilingual Support
    Generate voices in over 25 languages, including English (US, UK, AU, CA), Spanish, Japanese, Chinese, German, Hindi, French, Arabic, and more.

  • Custom Voice Cloning (Coming Soon)
    You’ll soon be able to create a custom voice from your own character’s recordings.

  • Emotionally-Aware Voiceovers
    Ideal for gaming, animation, narrative design, and professional content creation.


How to Use Voice Generation

  1. Select “Voice” as your audio type.

  2. Enter your script.

    • To generate audio in a different language, simply type your script in that language.

  3. Choose a character voice.

  4. Adjust Advanced Settings (optional):

    • Stability: Higher = more consistent, Lower = more expressive

    • Speed: <1.0 = slower speech, >1.0 = faster speech

    • Similarity: Enhances clarity and voice accuracy (higher = stronger)

    • Style Exaggeration: Boosts expressiveness, but may reduce stability

    • Speaker Boost (toggle): Improves resemblance to the selected voice

Once your settings are ready, click Generate to produce your voiceover.


Supported Languages

The ElevenLabs multilingual v2 model currently supports the following languages:

English (USA, UK, Australia, Canada), Japanese, Chinese, German, Hindi, French (France, Canada), Korean, Portuguese (Brazil, Portugal), Italian, Spanish (Spain, Mexico), Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic (Saudi Arabia, UAE), Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian, and Russian.


Sound Effects Generation

Sound effects are generated using a dedicated model trained to produce rich, high-quality soundscapes based on natural language descriptions.

How to Use Sound Effects

  1. Select “Sound Effect” as your audio type.

  2. Write a description of the sound you want (e.g., “glass breaking,” “sci-fi door opening,” or “underwater bubbles”).

  3. Adjust Settings:

    • Duration: Set to “Auto” or define a custom length (in seconds).

    • Prompt Strength: Controls how literally the sound effect follows your prompt.

      • Higher = more accurate

      • Lower = more variation and creativity

Then click Generate to create your sound effect.


What’s Next

We’re just getting started. Soon, you’ll be able to:

  • Sync voiceovers with generated video

  • Use audio directly in animated scenes

  • Clone voices from your existing characters

  • Control emotion, intonation, and delivery with even more precision

Stay tuned as we continue building a seamless, multi-modal creative experience.

Did this answer your question?