What can you create with Video with Audio?
Use this workflow when the soundtrack is part of the idea: footsteps in a hallway, traffic behind a conversation, or waves beneath a coastal shot. The generator offers Veo 3 Fast and Standard options. Audio is optional, so check the sound setting before generating a clip that needs it.
Scenes with ambience
Pair a visual setting with sounds such as rain, wind or a busy street. Describe what should be heard as clearly as what should be seen.
Dialogue concepts
Include a short line of dialogue and identify the speaker. Review the generated speech and timing before using the result.
Image-led video ideas
Use an image to guide the scene, then explain how the subject moves and which sounds accompany that movement.
How to use Video with Audio
Describe the scene and soundtrack
Write a focused prompt with a subject, action, camera direction and audio cues. Add an image if you want a visual starting point.
Choose a model and enable sound
Select a Veo option, turn on sound and check the credit cost shown in the form.
Generate and review
Sign in to generate, then play the result with sound. Check the visuals, speech and background audio before downloading.
Generation requires an account and sufficient credits. Costs vary by model and settings; review the estimate in the form and the pricing options before submitting.
Video with Audio prompt example
Use this sample as a starting point and adapt it to your own scene and inputs.
A close-up of a ceramic cup being placed on a wooden café table. The camera stays still. Audio: a soft ceramic tap, quiet café chatter and gentle rain outside. No music.
Keep the sound instructions specific. A short list of audible events is easier to evaluate than a vague request for cinematic audio.
Video with Audio FAQ
How do I generate AI video with sound?
Describe the scene and the audio you want, select a Veo model and enable sound in the form. Audio is optional and must be switched on for a sound-enabled request.
Is this the same as Speech to Video?
No. Video with Audio generates a scene with requested sounds. Speech to Video uses an uploaded audio recording and a character image to guide a speaking video.
Can I control every word and sound exactly?
Audio is generated from your instructions and may vary. Review pronunciation, timing and sound effects in the output; exact dialogue or synchronization is not guaranteed.
Related AI tools
Speech to Video
Turn a character image and a speech recording into an AI video with Wan 2.2. Upload your image and audio to guide the character’s speaking performance.
Text to Video
Create a video from a written scene description with Wan text to video AI. Start with a subject, an action and a setting, then add camera and lighting instructions.
Image to Video
Animate a photo, illustration or product image with Wan image to video AI. Upload your starting image and describe the subject movement and camera motion you want.