AI Tools Directory
Discover AI tools across categories
Zumbo
Open source local AI voice-to-text for Mac for private STT Discussion | <a href="https://www.producthunt.com/r/p/1263158?a
Voice Memo
Open-source voice notes that file your tasks and reminders Discussion | <a href="https://www.producthunt.com/r/p/1263
GhostDeck
Offline Mac music player with living low-poly worlds Discussion | <a href="https://www.producthunt.
JohnSnowLabs/spark-nlp
State of the Art Natural Language Processing GitHub stars: 4,158.
14 gentle mornings by Small WIns
Audio first physiotherapy delivered via WhatsApp Discussion | <a href="https://www.producthunt.
MIDIpad
You gamepad is a musical instrument Discussion | Link <
Gemini 3.8 text-to-speech models
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS Discussion | <a href="https://www.producthun
Speechka
Real-time voice translation that sounds like you Discussion | <a href="https://www.producthunt.com/r/p/1258470?app_id=3
Shootsolo 2.0
Voice-controlled camera + teleprompter for solo creators Discussion | <a href="https://www.producthunt.com/r/p/1257678
Robot Voice Bridge
Run ElevenLabs like a voiceover session, right on your Mac Discussion | <a href="https://www.producthunt.com/
Code-Amadeus/Amadeus
Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.15 α). GitHub stars: 236.
VoiceCap
The AI notetaker for meetings in your language Discussion | <a href="https://www.producthunt.com/r/p/1253025?app_id=339
TypeDash
Voice shortcuts and fast dictation for your desktop Discussion | <a href="https://www.producthunt.com/r/p/1254013?app
VoiceChanger.Live
Sound like anime girl in realtime on your next call Discussion | <a href="https://www.producthunt.com/r/p/1253
Shall We Talk
Voice dictation that saves transcriptions on iPhone and Mac Discussion | <a href="https://www.producthunt.com/r/p/
MosMos
Voice writing that works before, during, and after meetings Discussion | <a href="https://www.producthunt.com/r/p/1251122
Gemini 3.8 & 3.8 Live Extended Thinking
Our most advanced Gemini Audio models yet Discussion | <a href="https://www.producthunt.co
Voiskey
AI voice typing that sounds right in every app Discussion | <a href="https://www.producthunt.com/r/p/1237367?app_id=339"
OVO
Play local music, SoundCloud & streams across apple devices Discussion | <a href="https://www.producthunt.com/r/p/1239389?ap
VoxelWall
Music-reactive live wallpapers for Mac Discussion | Link<
Accordio
Give Claude your hours, invoices and contracts Discussion | <a href="https://www.producthunt.com/r/p/1247136?app_id=339
Devin Voice
You say it, Devin ships it Discussion | Link
Speechmark
Private, on-device meeting notes for Mac Discussion | Li
Desert Ant Labs
Small specialized AI models for speech, text, vision Discussion | <a href="https://www.producthunt.com/r/p/12461
morettt/my-neuro
This project lets you create your own AI desktop companion with customizable characters and voice conversations that respond in just 1 second. Features include long-term memory, visual recognition, voice cloning and LLM training. Compatible with various Live2D customizations. GitHub stars: 1,358.
Scriptly
An iOS teleprompter app controlled by your voice Discussion | <a href="https://www.producthunt.com/r/p/1241043?app_id=33
Assist
Voice annotate your Mac, get screenshots + clipboard manager Discussion | <a href="https://www.producthunt.com/r/p/1242
Bloop
Turn any Mac audio into a visual you can actually export Discussion | <a href="https://www.producthunt.com/r/p/1216716?a
Vincentwei1021/video-talkcraft
Agent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-level voiceover sync, 78 motion recipe cards, an anti-slideshow camera system, Remotion rendering. GitHub stars: 772.
Retold
Turn family voices into hand-drawn story films Discussion |
xzf-thu/VoiceMem
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level. GitHub stars: 644.
Parasocial
A fast, native podcast player for power listeners. Discussion | <a href="https://www.producthunt.com/r/p/1226022?app_
Happy Shrimp
Alibaba's AI music generator for turning ideas into songs Discussion | <a href="https://www.producthunt.com/r/p/123
Orato
Practice speaking. Your voice never leaves your phone. Discussion | <a href="https://www.producthunt.com/r/p/
ChordWeaver
Create, learn, and explore music through theory Discussion | <a href="https://www.producthunt.com/r/p/1228807?app_id
Glisio
Mac Recorder & Snap editor w/auto-zoom, audio, local MP4 Discussion | <a href="https://www.producthunt.com/r/p/1218794?ap
Speko
OpenRouter for Voice Discussion | Link
Gemini 3.5 Transcribe
Our most precise speech-to-text model yet Discussion | <a href="https://www.producthunt.com/r/p/1233386?ap
Local Music Organizer for Mac
Ultimate toolkit for local Apple Music library maintenance Discussion | <a href="https://www.produ
Flunkey
Voice-first AI layer for Windows (beta) Discussion | Link</
CostLogic
AI-powered construction takeoffs, estimates, and invoices Discussion | <a href="https://www.producthunt.com/r/p/121117
ChordViz
Build your own music visualizer for MIDI & audio Discussion | <a href="https://www.producthunt.com/r/p/1222530?app_id=3
VoiceGecko
Open source, local voice-to-text Discussion | Link
AI Group Call
Type a goal, join a live voice call with six AI minds Discussion | <a href="https://www.producthunt.com/r/p/121878
VoiceOS App Store
The app store for voice native apps that lives in your notch Discussion | <a href="https://www.producthunt.com/r/p/12183
Gesture Synth School
A practice app for learning to play music with your hands. Discussion | <a href="https://www.producthunt.co
Nexting-ai/nexting
A wearable terminal to dispatch tasks to your own AI agents — Claude Code, OpenClaw, Codex. Tap, speak, dispatch. The first hardware built for OpenClaw. Open source (MIT). GitHub stars: 506.
gesture.live
Play live electronic music with your hands using your webcam Discussion | <a href="https://www.producthunt.com/r/p/
yapyap
Own your voice again. Local-first voice & meeting recorder. Discussion | <a href="https://www.producthunt.com/r/p/11905
harry0703/MoneyPrinterTurbo
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow. GitHub stars: 101,009.
Mubert API
Edit tracks & stems, get consistent music with new engine Discussion | <a href="https://www.producthunt.com/r/p/1210445?a
Phantom Voice
Local push-to-talk dictation for Mac Discussion | Lin
Yap
Open-source voice dictation for Mac, fully on-device Discussion | <a href="https://www.producthunt.com/r/p/1210183?app_id=
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API. GitHub stars: 9,466.
Epilude
Local voice dictation for Mac for polished text Discussion | <a href="https://www.producthunt.com/r/p/1209468?app_id=339
SoundGate Guitar
AI Music Tutor that gives real-time feedback on your playing Discussion | <a href="https://www.producthunt.
Tunio
AI Music operations platform for venues Discussion | Link
Speech To Markdown
Harness local AI for notes Discussion | Link
Speechius
The teleprompter that actually listens Discussion | Link<
Liso
Highlight text on any page and turn it into audio. Discussion | <a href="https://www.producthunt.com/r
SMASH Voice to Invoice
Build and send quotes as fast as you can talk Discussion | <a href="https://www.producthunt.com/r/p/12032
PodcastorAI
Your AI twin hosts your video podcast Discussion | Link
UltraPod
Turn your old iPhone into a music-first dumbphone Discussion | <a href="https://www.producthunt.com/r/p/1201051?app_id=
Universal Dictation on Stream
Private Voice Ring for dictation across iOS & Mac Discussion | <a href="https://www.producthunt.co
BUD
Voice-first canvas for sketchnoting and whiteboarding Discussion | <a href="https://www.producthunt.com/r/p/120
Routine AI
Control work with your voice. The Siri for work. Discussion | <a href="https://www.producthunt.com/r/p/1198043?app_id=33
PieceKeeper
Track your music repertoire and practice Discussion | L
Backbeat Forge
Turn drum audio into a score you can actually edit Discussion | <a href="https://www.producthunt.com/r/p/1200821?
leon-ai/leon
🧠 Leon is your open-source personal assistant. GitHub stars: 17,366.
liampetti/fulloch
Fulloch - The Fully Local Home Voice Assistant GitHub stars: 120.
xvirobotics/metabot
构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。 GitHub stars: 919.
team-telnyx/telnyx-code-examples
Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs GitHub stars: 148.
hugohe3/ppt-master
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He GitHub stars: 39,672.
huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. GitHub stars: 162,629.
Jam-Pod
A player for people who keep their own music collection Discussion | <a href="https://www.producthunt.com/r/p/1196511?ap
sonichi/sutando
My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower. GitHub stars: 353.
kizuna-ai-lab/sokuji
Live speech translation powered by on-device AI and cloud providers — OpenAI, Google Gemini, Palabra.ai, Kizuna AI, Volcengine, and more GitHub stars: 982.
Open-Less/openless
Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字) GitHub stars: 2,728.
unslothai/unsloth
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. GitHub stars: 68,013.
Effects SDK
AI video & audio effects SDK for real-time apps Discussion | <a href="https://www.producthunt.com/r/p/1178725?app_id
Udio
AI music generation with licensed music, Magic Edit inpainting, and clean vocal separation
Suno
AI music generation — create studio-quality songs from text prompts, 44.1kHz output
ElevenLabs
AI voice synthesis with Eleven v3 — 70+ languages, audio tags, multi-speaker dialogue