Tag: tts
local offline text-to-speech synthesis tool
This utility provides local, offline text-to-speech conversion using the sherpa-onnx engine. It synthesises audio from provided text strings, requiring pre-configured runtime and voice models.
ElevenLabs TTS for Local Audio Playback
This command-line tool provides local playback access to ElevenLabs Text-to-Speech, supporting multiple models and custom voice selection. It allows advanced speech control via SSML-like tags for dramatic delivery, normalization, and struct…
Natural voice interaction for conversational AI
This skill enables natural, bi-directional voice conversations by integrating Speech-to-Text and Text-to-Speech capabilities. Developers can use the converse MCP tool to speak responses and listen for user input, supporting parallel executi…
Local Voice Cloning and Impression TTS Tool
This tool enables voice cloning for Text-to-Speech synthesis by training on short reference audio clips. It utilizes a local mlx-audio service (Apple Silicon only) to synthesize fresh speech in the cloned voice profile.
Local offline text-to-speech generation skill
This skill provides local, offline text-to-speech functionality using the sherpa-onnx CLI. It allows developers to generate high-quality audio files from text without requiring cloud connectivity or external APIs.
ElevenLabs TTS for Local Audio Playback
This CLI utility provides text-to-speech generation using ElevenLabs, supporting multiple models and advanced SSML-like tags for fine-grained audio control. It facilitates local playback and allows developers to define voice characters and …
Custom Voice Cloning and Impressions for VoiceMode
This skill enables voice cloning and custom impressions for VoiceMode by synthesizing fresh speech using a local TTS service. It requires a short reference clip and operates via the mlx-audio backend on Apple Silicon.
Local offline text-to-speech generation
This skill provides local, offline text-to-speech functionality using the sherpa-onnx CLI. It allows developers to generate audio files from text without requiring cloud connectivity or external APIs.
ElevenLabs Text-to-Speech Generation and Playback
This skill provides local playback for ElevenLabs Text-to-Speech, allowing developers to generate high-quality audio from text. It supports advanced delivery control via custom tags for emotion, pacing, and detailed normalization rules.