"Speech & Transcription" matching MCP servers:

Lets AI assistants work inside a running Adobe Premiere Pro: ~440 readback-verified operations behind nine tools. Every UI language Premiere ships, and it sees the frame: draws Object Masks on the people or parts it sees (click or lasso, add/subtract, tracking; macOS), checks keyframes frame by frame. Large skills library; built for Generative Extend, Generative Media, Object Mask, Enhance Speech.

Provides a local-first MCP tool surface for generating images and videos across dozens of Higgsfield AI models (Sora, Veo, Kling, Seedance, FLUX, Soul, and more), including Soul character training, speech/talking-head video, batch submission, job status polling, model recommendation and param validation, and account/history access. It routes requests across both the official REST API and the experimental cloud web backend with retries, circuit breaking, and typed structured output.