All models

ThinkSoundVideo

ThinkSound

Synced sound for a clip, from what happens on screen.

video/thinksound

ThinkSound

Video

Price
~1 credit / second
Typical time
about 8 min
Makes
Video to video

Best for

ThinkSound is an open video to audio model. It reasons about what happens in the clip and generates matching sound, guided by an optional prompt, and returns the clip with that sound.

  • Foley for a silent cutscene render.
  • A quick sound pass on many trailer clips.
  • Cut scene: generate the clip with Kling 4.0, then add sound with ThinkSound.

Put it together

Where ThinkSound fits in a game, with the models it works well with. Your agent runs every step.

Price

ModeModelPrice
Video to videoThinkSound~1 credit / second

Paid from your Summer credits; ~ marks a typical estimate for token-priced output.

Use it from code or your agent

Sign in once with summer login. Your agent or your code then runs it with your paid credits.

npx -y summer-engine@latest login
npx -y summer-engine@latest api run video/thinksound \
  --input '{"prompt":"a dragon circling a castle at dawn"}' \
  --download .

video/thinksound: $0.01 per second of video. Paid from your Summer credits.

Inputs

What input takes for video/thinksound. Send only what you need; Summer fills in tested defaults.

  • promptstringup to 4000 characters

    What happens in the clip. Needed without imageUrl.

  • videoUrlstringup to 2048 characters

    An input clip (public URL, at most 20 s): restyle or reframe it, move a character with its motion, or add sound to it (e.g. kling-video-to-audio). Billed on the clip's length.

  • aspectRatioenumDefault 16:9
    • 16:9
    • 9:16
    • 1:1
    • 4:3
    • 3:4
    • 21:9
    • 3:2
    • 2:3
    • auto
  • resolutionenum

    Only a quality the model offers; leave out for its default.

    • 720p
    • 1080p
    • 4k
    • 480p
    • 768p
    • 2k
    • 768P
    • 1080P
    • 480P

Model docs · Summer API docs · Set up the Summer MCP server · Try it in the browser

Questions

What is ThinkSound good for in game development?
ThinkSound is an open video to audio model. It reasons about what happens in the clip and generates matching sound, guided by an optional prompt, and returns the clip with that sound. Typical game uses: foley for a silent cutscene render; a quick sound pass on many trailer clips; cut scene: generate the clip with Kling 4.0, then add sound with ThinkSound.
How much does ThinkSound cost in Summer?
ThinkSound costs ~1 credit / second in Summer Studio. Prices marked ~ are typical estimates because the provider bills by tokens or output size. It is charged from your Summer credits.
What can ThinkSound generate, and how long are the clips?
In Summer, ThinkSound supports video to video. Video-to-video and motion-transfer results follow the length of your source clip.
Can I use ThinkSound from Claude Code, Cursor or Codex?
Not yet. ThinkSound runs in Summer Studio today. The Summer MCP server gives your agent summer_generate_video with its own model list, which does not include ThinkSound yet. See summerengine.com/mcp for setup.
Where do ThinkSound results go?
Every generation is saved to your Summer asset library. From there you can download it or bring it into a Summer Engine project.