Generate speech audio from text using sherpa-onnx with local voice models.
npx skills add https://github.com/chebizarro/swarmstr --skill sherpa-onnx-tts-chebizarro
Please help me install this Agent Skill. Skill: sherpa-onnx-tts Source: https://github.com/chebizarro/swarmstr/tree/main/skills/sherpa-onnx-tts Command: npx skills add https://github.com/chebizarro/swarmstr --skill sherpa-onnx-tts-chebizarro
This Skill provides a local, offline text-to-speech (TTS) solution, eliminating the need for cloud-based services and ensuring privacy and accessibility.
Use the sherpa-onnx-tts skill to convert the text "Hello from local TTS." into an audio file named tts.wav.
High-intent search queries and answers about installing and using this skill.
To generate text-to-speech audio offline, this Skill uses the sherpa-onnx runtime and pre-downloaded voice models to perform local speech synthesis, creating audio files without any cloud dependencies.
Yes, local TTS works completely offline. This Skill performs on-device speech synthesis using pre-downloaded models, ensuring functionality in sensitive environments or areas with poor connectivity without requiring cloud services.
To configure voice models for sherpa-onnx speech synthesis, you must set specific runtime and model directories using environment variables or flags, allowing the local TTS engine to locate and load the appropriate voice files.
Yes, you can use local text-to-speech to generate audio files for application interfaces. This Skill creates spoken feedback and audio pronunciations locally, making it ideal for voiceovers and offline application integration.
A limitation of using pre-downloaded models for offline TTS is that you must manually acquire and configure specific runtime and model directories before synthesis, restricting spontaneous voice or language switching without prior model downloads.
cogpyGenerate speech audio locally from text using Sherpa-ONNX runtime.
JoeyJoziahGenerate ElevenLabs speech audio from text with voice selection.
Probably-GroupGenerate local text-to-speech audio from sanitized text using Kokoro TTS.
TikTzukiConvert text to speech and transcribe audio via cloud APIs.
