Generate speech audio files locally using sherpa-onnx and VITS models.
npx skills add https://github.com/wangqianCAI/OBI --skill sherpa-onnx-tts-wangqiancai
Please help me install this Agent Skill. Skill: sherpa-onnx-tts Source: https://github.com/wangqianCAI/OBI/tree/main/skills/sherpa-onnx-tts Command: npx skills add https://github.com/wangqianCAI/OBI --skill sherpa-onnx-tts-wangqiancai
This Skill provides a reliable way to convert text into natural-sounding speech entirely offline, ensuring data privacy and eliminating the need for cloud-based API dependencies.
Run the sherpa-onnx-tts tool to convert the provided text into a high-quality audio file named output.wav.
High-intent search queries and answers about installing and using this skill.
Offline text-to-speech synthesis runs locally using the sherpa-onnx CLI and VITS models, converting text to audio without network dependencies. It generates high-quality speech files entirely on your machine for secure environments.
Yes, you can generate automated audio alerts from text logs offline. The local TTS synthesis engine processes text inputs to create audio files, making it suitable for automated alert systems in air-gapped or secure environments.
Yes, local VITS speech synthesis requires compatible ONNX model files. You must configure the runtime environment with these flexible voice models to achieve different vocal characteristics during the text-to-speech generation process.
The best way to ensure data privacy during text-to-speech conversion is using offline local synthesis. By processing text entirely on your machine without cloud-based API dependencies, your data remains secure and private.
Offline TTS limitations include requiring a pre-configured runtime environment and compatible ONNX model files. Without proper local setup, the synthesis engine cannot execute speech generation tasks for accessibility or media production workflows.
deepgramConvert text input to speech using Sherpa-onnx offline.
refly-aiGenerate MP3 or WAV audio from text using Fal.ai models.
malue-aiGenerate local text-to-speech audio with Kokoro TTS engine.
steipeteTranscribe local audio files to text or subtitles using the Whisper CLI.
