Tag: speech

Local neural text-to-speech engine that converts text to speech offline, with voices in dozens of languages, handy for listening materials or narrating articles and course slides. Needs Python; download a voice model before first use. The project is currently looking for maintainers.

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.

Two skills for FireRed's open-source conversational video editor OpenStoryline: the agent installs and launches it, then edits video from natural language, finding footage, writing script and voiceover, syncing music and revising. Needs Python 3.11+, ffmpeg (macOS/Linux/WSL) and LLM and vision keys.

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.

Turns a topic or article into a narrated explainer video in English or Chinese: research, script, voiceover, storyboard and per-shot animation, with subtitles and chapter cards. Needs Node.js, ffmpeg and Python; takes about 1-3 hours depending on length. Free for non-commercial use only.

Open-source local video editor with a multi-track timeline. Claude Code or Codex can rough-cut by chat, cut flubs and pauses from the transcript, and add subtitles, transitions and music as drafts you approve. Needs the desktop app with a project open; AI features need your own API keys.

From a single topic, the agent writes a storyboard, generates paper-cutout collage visuals, motion, narration, music and subtitles, and assembles a Vox-style explainer or ad with ffmpeg, checking with you on storyboard and style. Needs a prepaid Atlas Cloud API key, ffmpeg and Python.

A video production workspace for Claude Code: scripting, AI voiceover, music, generated visuals and Remotion rendering to MP4, with explainer and product-demo templates. The full workflow needs the cloned repo and Node.js 18+; AI generation needs your own cloud GPU (e.g. Modal's free tier).

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.

Local text-to-speech CLI built on the open Kokoro model: batch-converts TXT, EPUB and PDF to MP3 or WAV by chapter, with multiple languages, voice blending and speed control; handy for audio versions of course materials. Needs Python 3.11-3.12 and two model files downloaded first.

Translates a video's SRT subtitles into other languages and generates AI voice lines synced to the timings, producing translated subtitles and dubbed audio tracks. Needs Python, FFmpeg and Google Cloud, Azure, DeepL or ElevenLabs API keys; configure the ini files, then run python main.py.

MiniMax's official MCP: text-to-speech, voice cloning and voice design, text-to-image and video generation. Needs a MiniMax API key; the key and API host must belong to the same region (global or mainland China). Pay as you go.

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.

Stem separation CLI built on UVR models: splits audio into vocals and accompaniment in one command, isolates drums, bass and other stems, or removes noise and reverb; handy for stripping background music or extracting clean vocals. Models download on first use; needs Python and FFmpeg.

Adds voice conversations to Claude Code and other agents: speak, and it detects silence, transcribes, and reads replies aloud. Runs offline with local Whisper and Kokoro, or uses OpenAI's speech APIs; needs a microphone and speakers.

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.

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.

Experimental open-source generative media MCP servers from Google Cloud: Nano Banana images, Veo video, Gemini TTS and Chirp voices, Lyria music, and AVTool for compositing. Each registers separately; needs a billing-enabled Google Cloud project and gcloud login; AVTool needs FFmpeg.

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 video translation and dubbing: transcribes lectures, courses and other videos, translates them into one of 33 languages, synthesizes a dub aligned to the picture, and can export SRT subtitles. Needs Python 3.10+, FFmpeg, the violin CLI and a pay-as-you-go Together AI API key.

Official skill for BaoCut, a subtitle app by Baoyu: transcribe audio and video, generate and translate subtitles, check speakers, adjust timing and export SRT or finished video. Needs BaoCut on an Apple silicon Mac (macOS 14+); on Windows the skill fetches a preview CLI.

Drives a local ClipForge (open source) to turn product images, links or a one-line topic into vertical short videos with script, footage, voiceover, captions and music, plus a QA pass. Self-host it with Node.js and FFmpeg; scripts need an LLM (Ollama works); AI visuals need a paid key.

ChatCut's official plugin: edit ChatCut video projects by chat from Claude Code or Codex: import media, adjust the timeline, transcribe and caption, generate voiceover, music and motion graphics, and export. Needs a ChatCut account (free tier available); sign in via browser on first use.

Calls image and video models such as FLUX, Veo and Seedance through inference.sh's belt CLI to generate images, video, avatars and voiceovers, plus guides for thumbnails, storyboards, press releases and social copy. Needs belt and a free inference.sh account; model calls are billed per use.