Fork of @realtimex/piper-tts-web for easier built-in PiperTTS use (electron mostly)
Reliable TTS engine for DSH plugins: concurrency-safe synthesis, layered error semantics, chunked long-text, provider fallback, and an injectable ctx.tts service.
Google TTS(Text-To-Speech) for node.js
Text-to-speech (TTS) plugin for DeepSeek Harness — Fish Audio API only, bring your own key. Per-message read-aloud, auto-read toggle in the composer, an agent-callable audio-generation tool for chat channels, settings for model / voice / encrypted API key
Changes text into speech on your computer with the Kokoro TTS model: npx kokoro-cli Hello
Voice plugin for TheoKit — STT + TTS bridge with browser MediaRecorder helper + UI components.
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
让智能体拥有自己的声音:它决定什么时候开口说话,你决定接不接(接听/拒接/稍后再说)。语音全部在本机合成,首次使用需要在设置卡里一键部署本地运行环境。
Official Speko TypeScript SDK — one API, every voice provider
DSH web plugin: read aloud each DeepSeek turn output after spoken-style transcription (code/table/markdown aware), with per-message manual read buttons and an auto-read toggle.
ESM-first TypeScript SDK for the Breeze Blue Developer API.
A zero-dependency native Web Component accessibility preferences toolbar & assistive companion, built to W3C APG and WCAG 2.1/2.2 standards. The lightweight, privacy-first open-source alternative to UserWay & accessiBe.
Give Your Agent A Voice: x402 pay-per-call speech with 20 voices, 10 personas, 31 languages, granular speed and quality controls, OpenAI-shaped requests, and batch audio
Fully local, on-device text-to-speech Synthesizer for moxxy. Runs Supertonic 3 via sherpa-onnx in a forked sidecar process; the model downloads once on first use from sherpa-onnx's pinned releases (sha256-verified). No API key, no network at synthesis tim
Inline TTS (Text-to-Speech) tool component for PIE Players Assessment Toolkit.
MCP server for apimodels.app — call chat, image, video, speech, transcription, music, embedding and media models, plus the asset library, with one API key, from Claude Desktop, Cursor and any MCP client.
Native streaming text-to-speech on MLX
MCP server for the Lero voice API: Brazilian Portuguese speech inside Claude Code, Codex, Cursor and Claude Desktop.
The video studio your AI agent runs. Free on your own computer, with no account and no key.
Qwen TTS Realtime WebSocket client with audio playback
Build web apps with lifelike AI characters. The Convai Web SDK gives you real-time voice, lipsync, emotions, and dynamic context — with first-class support for React and vanilla TypeScript.
Official ContentHero SDK. Programmatic media generation (image, video, audio) on the ContentHero Studio API. The shared kernel the ContentHero MCP and CLI sit on.
A library for using Web Speech API with Angular
AdminForth audio adapter for OpenAI speech-to-text and text-to-speech.
Kokoro text-to-speech for pipedog: a port of Pipecat's KokoroTTSService, running the Kokoro-82M ONNX model locally through @pipedog/onnx with espeak-ng phonemization.
n8n node for Agent Data Tools: Word, Excel, PowerPoint and PDF files to text or Markdown, invoice and document fields as JSON, web search, page text, website audits, news, GitHub, CVE, company and sanctions checks, crypto prices and about 680 more tools b
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection [termux android-arm64 build with bundled .so]
青水AI营销创作平台 - 图片生成、视频生成、语音合成(TTS / 声音克隆)和静态资源分享 Skill
Together AI nodes for NodeTool — serverless image (FLUX / Imagen / Ideogram / Seedream), video (Veo / Sora / Kling / Seedance / MiniMax), text-to-speech (Orpheus / Kokoro / Cartesia) and transcription (Whisper / Voxtral / Parakeet)
Collection of reactive utility composables for Svelte 5 inspired by VueUse.
Runs voice conversations with live transcription, chat orchestration, and spoken replies.
Official Wiro AI SDK for React Native and Expo: run image, video, audio and LLM models with typed requests and live task tracking
Listen to GTFS stop names, flag incorrect pronunciations, and export a reviewed feed for tts_stop_name.
A powerful and straightforward Node.js module for generating AI speech audio files from text using the OpenAI API (support for other providers is in the works). ai-text-to-speech offers a simple and robust interface to convert text into high-quality speec
React Native Text-To-Speech module for Android and iOS
Character avatar, editable ID and read-aloud beside every assistant reply — system voice or your own TTS service (local or remote), with tone and speed controls, presets, a playback bar, one-click launching of your own TTS process, and a Chinese/English U
MiniMax AI nodes for nodetool
Permissionless communication supercharger MCP server — 40+ Lightning-paid tools: AI phone calls in any language, voice in 602 languages, translation across 119 plus 452 rare languages frontier models don't serve, fax, SMS, transcription, audiobooks, and m
The official Node.js REST API wrapper for Rymi.
Text-to-speech for the browser: a small wrapper around the Web Speech API with word-by-word highlighting.
OpenAI text-to-speech Synthesizer for moxxy. Text → spoken audio bytes via POST /v1/audio/speech. Plugs into the session's SynthesizerRegistry; read-aloud surfaces (desktop 'Read aloud', a voice channel) consume it transparently. The first shipped Synthes
Official MCP server for the Paxa Labs API: Thai, English, and Mandarin text to speech with local playback, speech to text with subtitles, translation between 15 languages, document OCR, and field extraction.
The official Node.js library for the Typecast API. Text-to-Speech with AI voices. TypeScript support included.
Long-form voiceover pipeline for DeepSeek Harness: chapter planning, spoken-script adaptation, subtitles, manifest, and resumable jobs. Turns a document into a publishable audio set.
CutPro MCP server: create images, videos, music, voices, sound effects, talking avatars and 3D with any AI model, AI characters, AI video clips, social scheduling and transcription
Browser-based English + Japanese TTS: kokoro-js (Kokoro-82M via transformers.js/ONNX) + openjtalkjs (Open JTalk G2P, WASM). No server or container required.
Customizable accessibility toolbar with text-to-speech, translation, reading tools and downloadable audio.