Инструменты

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.

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.

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.

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.

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.

Lets Claude Code watch videos: extracts frames with ffmpeg and transcribes timestamped audio from local files or YouTube links, to review footage, summarize lectures or find on-screen text. Needs Node.js 20+ and ffmpeg (yt-dlp for YouTube); transcribe with local Whisper or a Gemini/OpenAI key.

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.

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.

From Twilio Labs: exposes Twilio's public APIs (SMS, voice, phone numbers, Serverless and more) as MCP tools generated from its OpenAPI specs, with filtering by service or tag. Needs a Twilio API key; marked as a proof of concept.

Community-built MCP for the Genesys Cloud contact center: supervisors and QA staff can check queue volumes, sample conversations, and read call quality, sentiment, topics and transcripts. Needs an OAuth client in your Genesys Cloud org with per-tool permissions, and Node.js. Still in development.

Synthflow's official plugin: connects its AI voice agent platform to create and publish voice agents, place test calls and review call logs, with built-in call QA and pre-launch prompt review skills. Needs a Synthflow account (free trial available) with OAuth sign-in on first use.