STT on FOSS Engineer https://fossengineer.com/tags/stt/ Recent content in STT on FOSS Engineer Hugo en-US Sun, 14 Jun 2026 13:07:14 +0200 Local AI Voice Tools https://fossengineer.com/local-ai-voice-tools/ Sat, 06 Jun 2026 19:30:00 +0200 https://fossengineer.com/local-ai-voice-tools/ A chooser guide for Voicebox, KittenTTS, Chatterbox, and related local AI voice workflows, focused on what was actually validated locally. Voicebox - Local AI Voice Studio for Speech, Dictation, and Agents https://fossengineer.com/voicebox-local-ai-voice-studio/ Sat, 06 Jun 2026 10:50:00 +0200 https://fossengineer.com/voicebox-local-ai-voice-studio/ <strong>Voicebox</strong> is a local AI voice studio for cloning voices, generating speech, dictating into apps, transcribing captures, adding effects, composing stories, and giving AI agents voices through REST and MCP. It ships a Tauri desktop app, FastAPI backend, web UI, Docker setup, and multiple local TTS/STT engines. Chatterbox - Local Open-Source Text-to-Speech by Resemble AI https://fossengineer.com/chatterbox-local-open-source-tts/ Fri, 05 Jun 2026 11:45:00 +0200 https://fossengineer.com/chatterbox-local-open-source-tts/ <strong>Chatterbox</strong> is Resemble AI&rsquo;s MIT-licensed open-source text-to-speech toolkit. It ships Python APIs, Gradio demos, English and multilingual models, voice conversion, Turbo inference, paralinguistic tags, and built-in Perth watermarking. It is not a Docker-first self-hosted app; it is a local ML package where GPU access matters. ComfyUI-Qwen-TTS - Qwen3 Voice Nodes for ComfyUI https://fossengineer.com/comfyui-qwen-tts/ Thu, 04 Jun 2026 13:45:00 +0100 https://fossengineer.com/comfyui-qwen-tts/ ComfyUI-Qwen-TTS is a custom-node pack for running Qwen3-TTS workflows inside ComfyUI: text-to-speech, zero-shot voice cloning, designed voices, saved speakers, multi-role dialogue, and experimental fine-tuning.