voice-notes

Listening organs for AI companions: spoken voice-note cards and music cards that preserve what transcripts throw away.

The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes. User API via Telethon.

Local-first Plaud recording pipeline and personal knowledge timeline with Python, SQLite, Qdrant, RAG, 3D graphs, MCP tools, and a SwiftUI companion.

Pasithea 🧠 is an open-source voice journaling tool. the goddess of rest keeps your unfinished thoughts.

Voice note taking utility that uses cloud audio multimodal models for single pass transcription and text cleanup

🎤 System notatek głosowych z AI: transkrypcja OpenAI Whisper, wyszukiwanie semantyczne, embeddingi wektorowe. Aplikacja Python/Streamlit (Windows/macOS/Linux) z Docker, automatyczną kategoryzacją i eksportem PDF/DOCX/TXT. Enterprise-ready rozwiązanie do zarządzania wiedzą.

Unofficial Plaud Web workflow CLI for organizing account-owned recordings

Turn WhatsApp voice notes (and any audio) into clean text — Windows app using the OpenAI Whisper API with optional GPT cleanup. Ships as "Transcritor de Áudio de Zap".

Push-to-note voice capture for gameplay recording sessions.

Local, offline transcriber for Telegram & Instagram chat exports — voice/video notes via Whisper (faster-whisper), screenshots via OCR, photos/stickers/GIFs via a local vision model. Interactive menu or CLI; merges everything into one chronological, LLM-ready Markdown file. No cloud, no API key.

Pull your Plaud voice recordings into an Obsidian vault as triage-ready markdown notes

🎙️ Speak into your watch — find structured tasks in your notes. Headless, local-first daemon: transcribes voice memos on-device, splits one ramble into multiple intents, and routes each to its own destination. Zero clicks, zero cloud.

Turn voice notes into summaries + action items — handles Urdu-English code-switched speech. Local whisper transcription + Groq summarization, 100% free.

iPhone voice memos to transcribed Markdown in your Obsidian vault - iCloud Drive bridge + local faster-whisper transcription, no cloud transcription API

Hermes Agent plugin: auto-transcribe audio attachments (WhatsApp voice notes OGG/Opus, M4A, MP3...) so the agent can read them. Local faster-whisper, free & offline.

Local-first voice notes → faster-whisper STT + Anthropic tool calling → ~/Artifacts (AGPL-3.0)

AI voice notes prototype: turn raw voice notes into structured, useful outputs.

An open voice-to-note tool. Local voice notes: speak (or hand it a file) → faster-whisper transcribes on your GPU → a local LLM cleans it up → straight to your clipboard.

Voice -> text -> your personal knowledge base. A primitive, not a platform: 4 small Python scripts turn voice notes into linked, tagged, searchable markdown.

Turn raw voice transcripts into formatted Markdown notes, using a local LLM. Runs unattended, sends nothing off your machine.