Voice middleware
-
@lobehub/chat
Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
-
AgentCall
AgentCall is an open-source platform that lets AI agents call you when they need help. When an AI gets stuck — needs approval, clarification, or urgent input — it rings your phone via a real voice call. Chat, make decisions, and send the AI back to work. Self-hosted, private, no records. Works with Claude, Cursor, OpenCode, and any MCP-compatible.
-
agentwire-dev
A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.
-
AI-Audio-Content-Creator
Transform text into professional audio and podcasts using automated voice synthesis tools.
-
ai-podcast-clipper-saas
🎥 Create engaging short clips from podcasts using AI to boost visibility on platforms like YouTube Shorts and TikTok.
-
anamra
A native macOS capture-to-outcome workspace: screenshot, OCR, voice, AI-assisted drafts, local semantic memory, and confirmable Apple exits.
-
Aucards
Create reusable cards for quick access when non-verbal communication is needed.
Voice Android -
audio_align
🎧 Align audio to text effortlessly with precise word-level timing using OpenAI Whisper, outputting clean JSON for seamless integration.
-
aurum
Speech both ways. On-device by default. Local STT + TTS CLI, aurum-core, aurum-ffi.
-
baresip+
SIP and mobile calling and messaging User Agent for Android based on baresip lib
Voice Android -
ChineseTtsTflite
Chinese TTS Engine Based On Tensorflow TTS
Voice Android -
claude-tts
Convert Claude Code responses to speech using various TTS providers with local fallback for seamless audio output across platforms.
-
claude-voice
Local TTS voice mode for Claude Code with word highlighting and no cloud APIs.
Voice Python -
claude-voice-system
Add self-learning voice notifications for Claude Code with edge-tts, phrase pools, priority queues, and anti-repeat handling
-
Databag
A federated chat client designed for privacy and selfhosting.
-
dictator
Native macOS dictation with on-device or BYOK speech-to-text, LLM cleanup, screen-aware writing, global hotkeys, focused-field insertion, and a private clipboard.
-
dictidy
Rewrite selected text anywhere on your Mac with a global hotkey, using the Anthropic (Claude) API. Open-source menu-bar app.
-
Dictify
Hold fn, speak, get polished text anywhere on macOS. Native dictation powered by Groq Whisper + GPT-OSS.
-
Diktafon: Voice Memos on Tape
Voice memos on cassette tapes — transcribed & summarised offline, on device.
Voice Android -
Donate your voice: CV Project
This app permits you to contribute to Common Voice from your smartphone.
Voice Android -
easy-transcriber-stt
Transcribe audio and video locally or with cloud providers, with noise reduction, video support, and fast transcript output
-
ELI_v2.0
ELI
-
Ermis
Ermis M is an open-source, privacy focused mobile chat application.
-
fonos
A hotkey-first voice AI terminal for macOS & Linux: speak anywhere, transcribe, rewrite, capture notes/meetings, listen with TTS, and talk to AI agents using local or cloud models.
-
franken_whisper
Agent-first Rust ASR orchestration stack: Bayesian backend routing across whisper.cpp/insanely-fast-whisper/whisper-diarization, real-time NDJSON streaming, SQLite persistence, TTY audio transport, conformance harness. 107K lines, 2000+ tests, zero unsafe code.
-
Godot Whisper - Speech to Text
An addon for the Godot Engine that enables realtime audio transcription, supports OpenCL for most platforms, Metal for Apple devices, and runs on a separate thread.
Voice Godot -
haynoi
Push-to-talk dictation for macOS — Vietnamese-first, English-friendly. Hold a key, speak, text appears in any app. Powered by Kyma API.
-
hyperpolymath-v2
i brought back the rennaissance.
-
jarvis-voice
Personal self-hosted AI assistant. Voice control, 80+ tools, and autonomous coding. Cloud providers or fully local with Ollama. UI, CLI, TUI. Deterministic (code-driven) orchestration!
-
JianYan
🎤 Transform speech to text on Windows with fast, local AI processing. Enjoy seamless recording and automatic integration for effective communication.
-
julius
Two-pass large vocabulary continuous speech recognition engine
-
lala
Self-hosted voice & video chat built on LiveKit. E2EE rooms, screen sharing, no database, no accounts.
-
LeMontage
A pipeline-first workflow built for content creators: clips, reels, TikToks, shorts, podcasts and long videos. The goal is to become the TailwindCSS of content creation.
-
mente_digital
Assistente de voz 100% local (PT-BR): llama.cpp + RAG do vault Obsidian + anti-alucinação por controle de fluxo. Whisper, XTTS/Piper, barge-in, agentes falados. 824 testes sem GPU.
-
Meshenger
Voice- and video phone App for off-the-grid scenarios.
Voice Android -
miaoclaw-releases
🐱 Miaoclaw(喵喵)· 本地优先的中文桌面 AI 助手:办公文档交付 / 联网调研 / 语音纪要 / 手帐记忆 / 桌面宠物。此仓库发布 Windows 安装包与更新通道 | Local-first desktop AI assistant for Windows. Installers & update channel (binaries only).
-
movie-narrator
🎬 Generate narrated movie recap videos from a single prompt.
-
Muse - Text to Speech
Convert text to natural-speaking audio with custom voices and pauses
Voice Android -
n8n-nodes-palatine-speech
n8n node for integrating Palatine Speech API into workflow
-
Noise Suppression for Voice
Real-time Noise Suppression Plugin
-
Notely Voice: AI Voice to Text
A Notes and AI Voice Transcription app
-
Offline Translator
On-device translation of text, images and pdf/odt files, with TTS
-
Olvid
Private messaging for everyone
-
omnius
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
-
open-gpt-live
Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and experimental Ollama/local AI.
-
open-reader
Obsidian local TTS plugin for reading Markdown notes aloud with an offline text-to-speech CLI.
Voice TypeScript -
openai-whisper
General-purpose speech recognition model
-
OrgScript
Describe business logic, processes, rules, roles, and state transitions in a human-readable, machine-parseable text format.
-
pocket-tts
Text-to-speech application designed to run efficiently on CPUs
-
port-whisperer
See what’s running on your ports with a CLI that lists processes, PIDs, frameworks, and Docker containers
-
Read4SpeechExperiments
Read for Automatic Speech Recognition Experiments
Voice Android -
rexclaw
Rexclaw companions, grok realtime voice chat with VRM avatars that have persistent memory, gestures and emotions.
-
RHVoice - a speech synthesizer
TTS engine with extended languages support (incl. Russian)
Voice Android -
Sara-the-ai-assistant
Control your desktop with voice commands using this offline Python assistant powered by local LLMs and Whisper speech recognition.
-
sayeth
Spoken output for coding agents. Free and local by default via macOS say; ElevenLabs when you want the good voice.
-
SherpaTTS
Text-to-Speech engine based on Next-gen Kaldi
Voice Android -
sovereign-stack
Build your digital freedom stack with 5 guided phases for self-hosted apps, privacy, and full control of your online life
-
star
A keyboard-driven text-to-speech reading application designed for students with print disabilities.
Voice Python -
STT
Real-time speech-to-text with live translation, TTS, and a web UI — for church services, lectures & meetings
Voice Python -
stt-md
Lightweight macOS menubar app: mic → whisper → Ollama → Obsidian vault
-
Supertonic TTS
Local AI Text-to-Speech using Supertonic ONNX
Voice Android -
swift-toml
📄 Parse TOML configuration files easily with this robust Swift implementation, ensuring compliance and full support for all data types and structures.
-
talk-dat
Trigger-only Windows dictation overlay with BYOK speech models, local history, and an animated pill UI.
Voice Python -
TalkType
Privacy-first voice dictation for Linux Wayland — press a key to talk, release to type. Powered by Whisper AI, 100% offline, no subscription required.
Voice Python -
Transformers
State-of-the-art machine learning models for text, vision, and audio — pretrained and ready to use.
-
TRIfA
TRIfA Tox Client
-
Udderance AAC
TTS based AAC
Voice Android -
unofficial Stud.IP-app
An unofficial app for Stud.IP systems.
Voice Android -
Voice Audiobook Player
A clean audiobook player for your own files, with sleep timer and bookmarks.
Voice Android -
Voice Mail Player
Play media files through phone's ear-piece
Voice Android -
voicebridge
Hands-free, two-way voice for your coding agent (Claude Code, Codex, Antigravity, Ollama) from your phone — free for noncommercial use, source-available, no ElevenLabs. Browser Web Speech + a tiny Node bridge over Tailscale HTTPS.
-
voicegateway
Drop-in observability and cost-control layer for LiveKit voice agents
-
voicepad
VoicePad is a terminal-first voice note and transcription tool built with Python and Whisper. It records audio, generates local AI-powered transcriptions, and streamlines voice-based workflows through an ergonomic CLI and developer-friendly automation features.
-
vox-radio
設定ファイルから生成AI(Gemini)とVOICEVOXでラジオ番組(ポッドキャスト)の音声を自動生成するCLIツール
-
voxflow
Offline cotype.io: hold a hotkey, speak, and a local AI writes it in your voice and types it in. faster-whisper + Ollama, 100% on your machine.
-
whisperkit-cli
Swift native on-device speech recognition with Whisper for Apple Silicon
-
Wire • Secure Messenger
Wire offers highly secure communication – anywhere and anytime.
-
Wyoming Android TTS
Use your Android's TTS engines in Home Assistant via the Wyoming protocol.
Voice Android -
zoe-ai-assistant
Zoe - Your Local AI Life Hub & Personal Assistant
-
DexDictate_MacOS