Havuz

Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment.

Pretrained text classifiers you can run and retrain on CPU

A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

qwen2API çok dilli (i18n) fork'u • Multi-language (i18n) fork of qwen2API — WebUI artık Çince, İngilizce ve Türkçe / UI now in Chinese, Engl

hayamimi, specialist ASR modellerini dile göre yönlendirerek CPU üzerinde gerçek zamanlı, çok dilli konuşma dökümü ve canlı altyazı sağlar.

Neden yükseliyor · 34 günlük yaşına karşın 348 yıldız ve son 28 günde 112 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor. Ancak bu çalışma 3 farklı yazarla sınırlı; ilginin nedenini veya kalıcı benimsemeyi tek başına kanıtlamıyor.

MOSS-TTS-Nano, düşük kaynaklı cihazlarda çok dilli konuşma üretimi ve voice cloning için tasarlanmış 100M parametreli bir TTS modelidir.

Neden yükseliyor · 170 günde 4.412 yıldız alması, çok dilli TTS'yi GPU gerektirmeden çalıştırma ve voice cloning özelliklerinin geliştiriciler için çekici olduğunu gösteriyor. Ancak son 28 günde 2 commit ve 1 farklı yazar olması, yıldız ivmesinin güncel geliştirme etkinliğiyle desteklendiğine dair sınırlı kanıt sunuyor.

Token Cost Parity: Multilingual LLM Efficiency Analysis 2026

Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

跨 Agent、多语言面试准备 Skill | Codex · WorkBuddy · Claude | JD analysis, tailored answers, role practice & adaptive mock interviews

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewe

Don Cheli — SDD Framework. The most comprehensive Specification-Driven Development framework for AI agents. 88+ commands, 51 skills, 15 reas

Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown

🎬 Director-grade Seedance 2.0 prompt OS for OpenClaw + Hermes agents — 28 skills, T2V/I2V/V2V/FLF2V, multi-clip sequences, zh/ja/ko support,

AI skill for rewriting machine-generated text to sound human-written across 9 languages - 5-stage pipeline: cleanup → specificity → tone → r

Private, fully offline photo search for Android. Find photos with words in English, Arabic, French, Russian or Spanish, or with another phot

Multilingual source-grounded research workspace with agentic RAG, cited chat, podcasts, PowerPoint, and video.

AWS-native knowledge graph RAG framework unifying two graph-retrieval methodologies — Microsoft GraphRAG community summarization and LightRA

Infinite text-free AI image generator + SQLite-indexed multilingual vault & gallery — with a local MCP your AI can drive.

A high-accuracy, multilingual rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accur

SEO Content Engine for LLMs - a prompt-engineering system that turns any capable AI into a world-class SEO strategist: generate, rewrite, an

Self-hosted multilingual (English + 5 Indic) phone voice agent template - LiveKit Agents + Sarvam STT/TTS + OpenAI + Vobiz SIP. ~700ms-1.2s

Gravitas is a free add-on for Google Antigravity that makes its AI agent check what your answer depends on, tell you kindly when something y

A local, multi-voice audiobook generator: an LLM casts every character in its own voice, kept consistent across a whole series — with voice

Pixel-precise DOM inspector that turns any element into a ready-to-run AI coding prompt. Works with Claude Code, Cursor, Codex. macOS native

Spring AI multilingual customer-service Agent platform for cross-border ecommerce, with RAG, order tools, escalation, and Vue admin UI.

Is there one workspace, or twin workspaces? Testing cross-lingual generalization of the J-space / global workspace in language models.

This is a comprehensive tool for merging, analyzing, and training Anima models (cosmos) in a hierarchical (layer-by-layer) manner.Multilingu

Language-specific AI writing pattern detectors for Claude Code, ChatGPT, Cursor and other AI tools. Statistically grounded — not translated

Real-time Windows system-audio translation captions for Chinese, Japanese, English, and Korean, with optional LLM revision.

Reply to Instagram comments with your AI assistant — the program only fetches & sends, the AI drafts replies in chat. No paid AI API.

Back to flow. Hold Fn, speak, and your words land at the cursor. Local-first dictation for macOS in 30+ languages.

A multilingual Agent Skill Pack that turns AI agents into guided learning coaches.

Voice agents that speak your caller's language: listening, turn-taking, barge-in and the voice, in 29 languages. Open source.

Privacy-first AI novel writing IDE. Full workflow: outline→draft→review→finalize. Local RAG + multi-model routing. Trilingual UI (zh/en/ru)

Evidence-assisted Yu-Gi-Oh! rulings for OCG and TCG, with card-text checks and cited sources. TCG public preview.

✨ Multilingual AI product copy from images. Responsive writing studio, translation, accounts, credits and automatic setup with optional Dock

Free neural text-to-speech (TTS) for Markdown in VS Code — no API key, 75 languages.

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cl