This skill helps developers integrate Runway's audio API capabilities into server-side applications. It documents available models and endpoints for text-to-speech, sound-effect synthesis, voice isolation, dubbing, and speech-to-speech conversion, and provides example code snippets for Node.js and Python and integration patterns for Express and FastAPI. The skill focuses on practical implementation details like uploading local media, handling output URLs, and cost considerations.
Use when adding audio generation or processing features to a backend: generating TTS, producing programmatic sound effects, isolating voices from noisy audio, dubbing media into other languages, or performing voice conversion. Ideal for teams building accessibility features, automated dubbing, or creative audio generation pipelines.
Best for developer-assistant agents and coding automation that can edit server code, manage API keys, and run backend tests (e.g., Copilot-style coding assistants and CI-integrated build agents).
This skill has not been reviewed by our automated audit pipeline yet.
