Speakr transforms audio recordings into organized, searchable, AI-enhanced notes with speaker recognition that identifies who said what across your entire recording library. The Python/Flask backend with Vue.js 3 and Tailwind CSS frontend deploys via Docker on port 8899, offering multiple transcription engines through auto-detected connectors: WhisperX for local processing with speaker diarization and voice embeddings, OpenAI Whisper and GPT-4o-transcribe, Mistral Voxtral for cloud diarization, AssemblyAI for multi-hour files, and any custom ASR webservice. Speaker voice profiles use embedding comparison to recognize individuals across different recordings automatically, while custom vocabulary biases the transcriber toward domain-specific jargon. The AI layer goes well beyond transcription: customizable summaries with per-recording, per-tag, and per-folder prompt templates; event extraction surfacing action items and calendar events; per-recording chat with streaming responses; and Inquire Mode for semantic search and natural-language queries across your entire library simultaneously. Smart tags execute custom AI prompts on transcripts for automatic categorization. The REST API with Swagger documentation supports signed webhooks integrating with n8n, Zapier, and Make. Auto-export pushes to Obsidian and Logseq, auto-processing watches directories, and the installable PWA provides mobile-first, offline-capable access with share-target support. 3,600+ stars since May 2025. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Audio lectures become structured, Markdown-formatted notes in about a minute with ScribeWizard (also known as GroqNotes). Upload an MP3, WAV, or M4A file - or paste a YouTube link - and the app runs a three-stage pipeline on Groq's LPU inference hardware: Whisper Large v3 transcribes the audio, a larger Llama model drafts a comprehensive outline of the material, and a faster Llama model fills each section with detailed content. This scaffolded prompting strategy is the core idea: the strong model handles structure where quality matters most, the fast model handles volume, and Groq's 1200+ tokens-per-second inference keeps the whole process near real time. Output renders as clean Markdown with support for tables and code blocks, and finished notes download as text or PDF. Model selection is configurable - swap in other Groq-hosted open models like Mixtral or Gemma to trade speed against quality or work around rate limits. Built as a single Streamlit app by Benjamin Klieger at Groq, it needs only a Groq API key to run, making it one of the simplest self-hosted AI tools to operate.

Vexa is the only Apache 2.0 meeting bot API that self-hosts the complete transcription pipeline, from bot dispatch to Whisper speech-to-text to knowledge agents, with zero audio leaving your infrastructure. A single POST /bots request sends a transcription bot into any Google Meet, Microsoft Teams, or Zoom call, where it captures audio, runs speaker-attributed transcription through faster-whisper or any OpenAI-compatible endpoint, and streams results to your application via real-time WebSocket with sub-second latency. The built-in agent framework watches live transcripts and your accumulated workspace context, answering mid-call questions grounded in your own meeting history and wiki. An MCP server connects Vexa to Claude, Cursor, and other compatible AI tools, turning every captured meeting into queryable context for external agents. The Terminal, a bundled Next.js web workbench, lets you send bots, watch live transcripts, manage users and API tokens, and chat with your meeting archive from a browser. Docker Compose brings the full stack up on one Linux host in five minutes; the Helm chart scales to thousands of users on Kubernetes with a Pod-per-bot architecture and built-in RBAC. Recordings persist in MinIO or any S3-compatible store, transcripts in Postgres, with Redis handling queues and scheduling. Deploy on RepoCloud for a dedicated VPS with full root SSH access and browser console. Apache 2.0 licensed.

Kokoro-FastAPI turns text into natural-sounding speech across eight languages by serving the 82-million-parameter Kokoro-82M model through an OpenAI-compatible REST API, so any existing OpenAI SDK client can generate audio by just changing the base URL. With over 5,300 GitHub stars since December 2024, the fully Dockerized FastAPI server covers American English, British English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese with language-specific phoneme processing. Inline voice mixing blends multiple profiles using weighted ratios like af_bella(2)+af_heart(1), automatically normalizing weights and caching combined voicepacks as PyTorch tensor files for reuse. Audio streams in real time over HTTP with configurable chunk sizes, or generates complete files in MP3, WAV, OPUS, FLAC, AAC, or PCM formats with speed control from 0.25x to 4.0x. Per-word timestamped captions with speaker-tagged voice labels enable subtitle generation for podcasts, audiobooks, and accessibility workflows. Pre-built Docker images support NVIDIA GPU acceleration via CUDA, experimental AMD GPU inference via ROCm, and CPU-only deployment on linux/amd64 and linux/arm64 architectures, with Apple Silicon MPS support available through direct UV execution. The integrated web interface at port 8880 provides browser-based speech generation, while the Swagger UI at /docs exposes the full API reference. Debug endpoints report system statistics for monitoring inference load. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.