"Spec-WorkFlow documentation or implementation" matching MCP servers:

Enables local, offline, CPU-only transcription of video/audio into timestamped SRT subtitles with Whisper, Chinese TTS dubbing (including multi-speaker dialogue), and synthesis of a new dubbed video in a single command. Supports dubbing silent videos, translating and re-voicing foreign-language videos, and batch-adding narration to short clips within AI workflows.

MCP server for audio transcription using OpenRouter models, supporting verbatim, cleaned, and custom transcription modes.

Enables fault-tolerant German address capture for phone agents by matching speech-recognized street names against the official directory and returning confidence scores with TTS-ready follow-up prompts.

A Model Context Protocol (MCP) server that gives AI agents the ability to process audio files — transcribe speech to text, detect spoken languages, and extract audio metadata.

Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.

MCP server for SpeechWeave transcription, enabling AI assistants to transcribe local files and URLs via wait-first or async tools.

MCP server for Whipscribe — transcribe audio and video from a URL or local file via Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP-compatible client.

Enables MCP-capable assistants to transcribe local audio files or URLs and perform speaker diarization for Spanish and Portuguese audio, with options for speaker count hints, domain prompts, and transcript retrieval in multiple formats.

Local-first CLI + MCP server for meeting recordings - Whisper transcription,

Enables coding agents to participate in voice calls, speaking replies while continuing their work and accepting spoken input or interruptions within the same conversation. It delivers voice input into Claude Code, Codex, Cursor, or custom HTTP endpoint workflows.

Transcribe public videos and audio (YouTube, TikTok, Instagram, Facebook, Pinterest, Google Drive) into accurate, timestamped text from Claude, ChatGPT, Cursor or any MCP client. Spanish, English and dozens of languages auto-detected. Poll-based (transcription takes minutes), same free-beta limits as the app. Docs: https://justtranscribe.ai/mcp

Enables supported local AI clients to control a visible desktop presence through bounded presentation tools such as animations, window control, and short local speech over a loopback endpoint, without granting decision or execution authority.

Provides voice summaries after each AI request in Cursor, Cline, or any MCP-supported editor, allowing users to hear what was done and stay informed without staring at the screen.

Enables assistants to open scripts in a centered, multilingual reader with direct paste, locale-aware word tracking, manual sentence navigation, pause/auto-scroll, and optional browser or OpenAI speech recognition.

MCP server that turns video URLs into transcripts and important keyframes locally, with no cloud or API keys.

Fetches YouTube transcripts and metadata (title, channel, duration) for URLs, using subtitles or on-device Whisper STT when no subtitles are available, enabling chat-based YouTube video analysis.

Local Korean text-to-speech MCP server using a fine-tuned CosyVoice2 model, enabling voice synthesis directly from Claude or Codex with privacy and no API costs.

Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices.

Enables MCP clients to place, monitor, and hang up phone calls through authenticated tools, retrieve transcripts, and exchange correlated task results with a waiting host. It supports simulated or live calling with persisted call lifecycle records, duration limits, and idempotent requests.

YouTube MCP by SocialDataX for video search and details, comments and replies, channel profiles and uploads or Shorts, and speech-to-text transcripts.