Blueprint by Mozilla.ai on how to transcribe audio files
-
Updated
Jun 13, 2025
#
speaches
Here are 9 public repositories matching this topic...
Speaches Reloaded — OpenAI-compatible self-hosted STT/TTS with transcribe.cpp, optimized Docker images for CPU, AMD/Intel Vulkan and NVIDIA CUDA
-
Updated
Sep 19, 2026 - Python
Self-hosted voice notes → Markdown for Obsidian. Quick transcription + watch folders with Whisper, Speaches or any OpenAI-compatible STT.
docker markdown rust automation self-hosted note-taking speech-to-text obsidian whisper pkm homelab knowledge-management voice-memos voice-to-text audio-transcription voice-notes audio-to-text sveltekit openai-compatible speaches
-
Updated
Sep 19, 2026 - Rust
Local-first script-to-audio authoring and rendering for external Speaches text-to-speech servers.
-
Updated
Sep 18, 2026 - TypeScript
Turn-key Docker stack for self-hosted Open Notebook with host Ollama, Speaches TTS/STT and SurrealDB - chat, embeddings, podcasts, no API key required.
docker docker-compose self-hosted embeddings tts stt whisper turnkey open-notebook kokoro surrealdb ai-tools llm local-ai ollama notebooklm speaches
-
Updated
May 1, 2026 - Python
Self-hosted speech-to-text with Whisper, faster-whisper and Speaches. Docker stack with regression-tested model unload fixes and shared GPU lifecycle integration.
docker gpu cuda inference self-hosted speech-recognition vad speech-to-text transcription whisper asr mlops faster-whisper speaches
-
Updated
Sep 13, 2026 - Python
Solução desenvolvida para o desafio DIO × Globant — Java & Spring Boot AI Developer.
-
Updated
Jun 13, 2026 - Java
A flexible Docker Compose setup for running AI tools locally with optional external API support. Choose complete privacy with local models or connect to cloud providers when needed.
-
Updated
May 22, 2026
Add this topic to your repo
To associate your repository with the speaches topic, visit your repo's landing page and select "manage topics."