Text to speech

🤖 Real-Time Voice Telemetry & Dynamic Audio Ducking Engine for AI Coding IDEs. Zero-silence agentic execution with JARVIS neural voice.

The open-source AI voice studio. Clone, dictate, create.

For people with aphasia: describe the word you can't find, tap the right guess, hear it said. It only picks from a fixed word list plus your own names, using Jev by TypeSafe.

Hand-drawn animated explainer videos made entirely with code — canvas JS visuals, synthesized music & SFX, AI voiceover, rendered with headless Chrome + ffmpeg.

A hands-free, recorded video call with Claude: Claude Code for the thinking, ElevenLabs for voice, generated visuals, edit-ready recordings.

Turn a research paper into a short audiobook. Guidelines for agents, one tool for the voice.

OpenAI-compatible speech serving in Rust

把一个主题做成有配音、字幕、封面的讲解分析类视频 —— 全本地、用 HTML 写画面，稳定音画同步。 面向 AI 编程智能体的确定性 HTML → MP4 渲染流水线。

Self-hosted, single-owner backend for the Cedar read-aloud app (FastAPI + Kokoro TTS). One key, one library, any number of devices.

Yvette, a local, open-source AI companion and low-VRAM voice avatar. Real-time talking-head with voice cloning & design and multi-engine TTS.

OpenCode V2 plugins. First package: xAI SuperGrok extras (web search, X search, Grok Imagine, STT, TTS).

不露脸商业/消费调查长片的完整生产流程：一句话出 10 分钟成片，以 Claude Code skill 形式开源（TTS 逐字时间戳、素材覆盖、Remotion 拼贴、闪避混音、封面与八平台文案）

DeskPilot is a native Python/Tkinter AI desktop app. Connect to any OpenAI-compatible server to unleash agentic tools: mcp, web search, secure file I/O, JS sandboxing, screen capture, and local image generation. Features local Whisper dictation, Kokoro TTS, streaming Markdown and creates a new chat session with handoff notes when context is full.

Local text reader with offline TTS and phrase-by-phrase controls.

Self-hosted voice agent runtime: speech-to-text, an LLM and text-to-speech streaming into each other in one process.

Fully offline voice assistant on ESP32-S3 (Freenove FNK0104B): free-form STT, tiny LLM, TTS