"Speech & Transcription" matching MCP servers:

MCP server that analyzes TTS audio recordings, providing transcription, quality scoring, pacing analysis, and mispronunciation detection to debug voice call center audio.

Enables AI assistants to inspect what NVDA reads and says, including focus, accessibility trees, document text, and speech history, and optionally to perform keyboard actions that NVDA announces as if the user pressed them.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

An MCP server that audits voice-assistant tools for prompt injection, tool poisoning, privacy leaks and speech-unfriendly answers. It exposes scanning, PII/link checks, voice rewriting and server-audit tools so users can test whether MCP tools are safe and voice-ready.

Enables end-to-end testing of voice-enabled web applications by simulating a synthetic user with a virtual microphone, virtual speakers, a real browser, and a viewable display, allowing audio injection, speech capture/transcription, and browser automation.

Examines web pages through screen-reader actions and speech, enabling agents to perform accessibility checks and interact with page content.