Havuz

DramaClaw, senaryodan storyboard ve görsel varlıklara, oradan tamamlanmış videoya uzanan AIGC video üretim akışını tek bir self-hosted uygulamada birleştiriyor.

Neden yükseliyor · 185 günlük bir repoda 6.542 yıldızın yanı sıra son 28 günde 74 commit ve 10 farklı yazar bulunması kayda değer ilgi ve güncel geliştirme gösteriyor. README'deki örnek yapımlar da soyut bir demodan fazlasını sunduğuna dair proje içi kanıt sağlıyor; yine de yıldızlar gerçek kullanım veya bağımsız benimseme kanıtı değil.

Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) r

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Turn the daily TLDR newsletters into a podcast. Local, deterministic, no LLM.

Your free book and audiobook laboratory. Turn the PDFs you own into chapter-marked M4B audiobooks, read-along books and bilingual editions,

Local, open-source (Apache 2.0) voice layer for Claude Code and Codex on macOS that reads your coding agent's progress aloud. Kokoro text-to

Open-source AI pipeline that turns any topic into a publish-ready YouTube/Instagram/TikTok Short — research, script, voiceover, visuals, mus

macOS desktop widget for Claude Code. See what Claude is doing, respond by voice, never miss a permission request.

AI 解说大师 — CLI 客户端；用于终端调用视频解说生成 API

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work t

Agent skills for daily use

Single-container self-hostable Readest fork — SQLite + local FS, no Supabase, no paywall. Community: https://nodebyte.cn

Kesha listens and talks back: local speech to text and text to speech for agents and scripts, fastest on Apple Silicon.

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custo

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

The One Dashboard every Voice Agent needs

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP +

The Humanness Index: the open benchmark for how human voice AI sounds, built by Vapi. Blind same-voice battles, pure-vote Elo, with a real-h

Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.c

Local-first AI voice studio: offline text-to-speech, multi-take editing, WAV/MP3 export. No cloud, no GPU needed

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

Local TTS voice mode for Claude Code with word highlighting and no cloud APIs.

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

crawl4ai for video & audio — turn any YouTube video, podcast, or recording into clean timestamped markdown, or a verified TTS/STT training d

Accepted at ISCSLP 2026 · Target-level benchmark for raw-input Chinese news TTS pronunciation

日本語フリガナ (ルビ) を扱う Rust 製ライブラリ + ローカル HTTP サーバー。ルールはすべてデータ駆動 (TOML)。

Easy access to speech data across 142 African languages for training TTS and ASR models.

AI 音频工作台：Apple Silicon 本地 TTS、语音克隆与音色设计，另支持 Suno 音乐生成。 / AI audio workbench with local Apple Silicon TTS, voice cloning, voice design, and S