Lightricks
lightricksLightricks has one model in the ModelRunner catalog: LTX-2.3 Text-to-Audio, a Sound endpoint, priced at $0.1 per second of audio — generate sound effects and ambience with set durations.
1 public model — runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Lightricks models & pricing
What you can build with Lightricks models
- Generate sound effects and ambience with set durations LTX-2.3 Text-to-Audio
- Create audio beds for video edits from text LTX-2.3 Text-to-Audio
- Produce spoken-style audio snippets for prototypes LTX-2.3 Text-to-Audio
Browse by capability
Use Lightricks models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Lightricks model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Lightricks models can I run on ModelRunner?
The catalog has 1 public Lightricks model: LTX-2.3 Text-to-Audio. It covers sound. It has its own page with a free playground, the full input schema, and copy-paste code.
How much do Lightricks models cost?
Pay-per-use, with no subscription: the one Lightricks model billed per second of audio costs $0.1, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Lightricks model from the API?
POST to https://queue.modelrunner.run/lightricks/ltx-2.3/text-to-audio with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Lightricks model from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and Lightricks's model becomes a tool your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.
Other creators in sound
- resemble-ai (5)
- elevenlabs (2)
- google (1)
- hexgrad (1)
- Meta (1)
- minimax (1)

