도구

OpenAI's open-source general-purpose speech recognition model. The whisper command transcribes many languages, translates foreign speech into English and writes subtitle files. Needs FFmpeg; faster with a GPU.

C/C++ port of OpenAI's Whisper speech recognition model that transcribes audio offline and outputs subtitles. Runs on CPU, with Apple Silicon and various GPU acceleration. Download a ggml-format model first.

Fast speech transcription built on faster-whisper, with word-level timestamps and speaker diarization, suited to meeting notes and subtitles. Diarization needs a Hugging Face token; GPU acceleration needs CUDA.

Offline speech transcription and translation based on Whisper; audio never leaves your machine. buzz add exports lectures, interviews and meeting recordings to TXT, SRT or VTT. pip install needs Python 3.12 and FFmpeg; a desktop app is also available. Check transcripts manually.

Continuously records your screen and audio locally, extracting on-screen text and transcribing speech, so agents can search pages, docs and meetings you saw and summarize your day. Data stays local. Needs screenpipe running: source is free for personal use, desktop app is a subscription.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

Official MCP from the FunASR project: transcribes audio files locally with the SenseVoice model, supporting Mandarin, Cantonese, English, Japanese and Korean, with optional segment timestamps. Local inference needs no API key and audio stays on your machine. Docker image available.

Unofficial Python library and CLI for driving Google NotebookLM (now Gemini Notebook): bulk-import sources, ask cited questions, and generate and download podcasts, videos, slides, quizzes and flashcards. Ships an agent skill. Relies on undocumented APIs and needs a Google sign-in.

Open-source zero-shot TTS via f5-tts_infer-cli: from a few seconds of reference audio it reads Chinese or English text in the same voice, handy for lessons and videos. Needs Python, PyTorch and FFmpeg, ideally a GPU. Pretrained models are non-commercial; get consent before cloning a voice.

Official skill for Anarlog (formerly Hyprnote), an open-source, local-first meeting notes app: lets agents query notes, summaries, transcripts, attendees and action items from local data, with no meeting bot needed. Requires the Anarlog desktop app and CLI; remote cloud access needs Pro.

Offline speech toolkit for Apple Silicon Macs: CLI text-to-speech (including Chinese and voice cloning) and speech-to-text, for voicing lessons and explainer videos or transcribing lectures and interviews, with data staying local. Needs an M-series Mac and Python 3.10+; MP3 export needs ffmpeg.

Gemini API development skills: gemini-api-dev (core API and SDKs), gemini-live-api-dev (real-time bidirectional audio/video streaming) and gemini-omni-flash-api (Omni video generation and editing), filling in APIs released after model training cutoffs. Maintained by Google's Gemini team.

Open-source meeting bot and real-time transcription platform: sends a bot into Google Meet, Teams or Zoom and transcribes live by speaker, with MCP so agents can dispatch bots and read transcripts. Use the hosted service (API key) or self-host.

MiniMax's official CLI, built for agents: chat with MiniMax models from the terminal and generate images, video and speech, plus speech transcription, image understanding and web search. Works with the international platform. Requires a MiniMax Token Plan subscription.

Audio plugin suite: transcription with local Qwen3-ASR or Whisper (MLX on Apple Silicon), speaker diarization, transcript correction, structured meeting notes and StepFun TTS. StepFun ASR and TTS need an API key.

Local transcription that's compatible with the OpenAI Whisper CLI but faster and lighter: outputs SRT/VTT subtitles or text and can transcribe a live microphone. Needs Python; models download on first run; speaker labels need pyannote.audio and a Hugging Face token.

Turns ComfyUI workflows into MCP tools with no code, covering generation and conversion across text, image, speech and video; works with local ComfyUI or RunningHub in the cloud. Start the server with uvx pixelle and configure an LLM first.

Open-source meeting connector that lets agents join Zoom, Teams or Google Meet as a participant, read the live transcript, chat and attendee list, and speak, e.g. to take meeting notes. Runs locally in Docker (image about 2.3 GB); transcription is local by default.

Official ElevenLabs skills: text to speech, speech to text, sound effects and music generation, voice changing, vocal isolation, multilingual dubbing and building voice agents. Needs an ElevenLabs API key.

Spotify's official plugin: agents script and voice content such as morning briefings, meeting recaps or article explainers into audio episodes with cover art and a timeline, saved to Spotify. Needs the save-to-spotify CLI and sign-in; voices can use free local Kokoro.

Official iFlytek skills: machine translation, video translation and dubbing, Chinese document proofreading, PDF, image and invoice OCR, speech-to-text and TTS, plus contract review (lawyer check needed). Needs iFlytek open platform services and keys; contract review also needs OCR and LLM APIs.