local-tts

Plugin local-tts in danielrosehill/Local-TTS-Plugin. Commands read from the repo's manifest — 5 days ago.

Skills (8)

• choose-engine

  Pick which local text-to-speech engine to install on this machine (Kokoro for low-resource CPUs, NeuTTS Air for CPU voice cloning, Chatterbox for GPUs with CUDA or ROCm) from its detected hardware, and say what is already installed. Use for "set up local TTS", "which TTS model should I use here", "w

• clone-voice

  Clone a voice in one shot from a single reference recording and save it locally as a reusable voice profile (a stored embedding), on CPU with NeuTTS Air or on a GPU with Chatterbox. Use for "clone my voice", "make a voice from this recording", "use this person's voice", "add a voice", "delete that v

• read-aloud

  Speak text out loud right now through the speakers with a local TTS engine. It can read the last reply, a passage on screen, the clipboard, the highlighted selection, or a file, with no file kept. Use for "read that out", "read this to me", "say it out loud", "read my clipboard", "read the selected

• setup-chatterbox

  Install Resemble AI's Chatterbox text-to-speech (Turbo by default; also standard, multilingual and the CPU Nano) on a GPU machine, with the right PyTorch build for AMD ROCm, NVIDIA CUDA or CPU, then smoke-test it and record it in the local TTS registry. Use for "install Chatterbox", "set up Chatterb

• setup-kokoro

  Install Kokoro-82M, the small fast local text-to-speech model, on CPU via kokoro-onnx (no PyTorch, no GPU) if it is not already installed, download the model, smoke-test it and record it in the local TTS registry. Use for "install Kokoro", "set up lightweight TTS", "local TTS for my laptop", or when

• setup-neutts

  Install NeuTTS Air (Neuphonic, Apache-2.0), an on-device voice-cloning TTS model that runs on CPU from a quantised GGUF backbone, register its bundled sample speakers and smoke-test it. Use for "voice cloning without a GPU", "clone a voice on my laptop", "install NeuTTS", or when choose-engine picks

• text-to-audio-file

  Turn text, a markdown document or a script into an audio file (WAV, MP3, OGG/Opus, FLAC, M4A) with a locally installed TTS engine and voice, including cloned voices. Use for "make an MP3 of this", "generate a voiceover", "convert this document to audio", "TTS this file", "save it as audio".

• tts-status

  Show which local text-to-speech engines, model variants and voices (preset and cloned) are installed on this machine, set the default engine, voice and output folder, re-run smoke tests, or remove an engine. Use for "what TTS do I have", "list my voices", "make Chatterbox the default", "set my defau

Similar plugins