Generate on-device speech from text using sherpa-onnx.
npx skills add https://github.com/Zentin-L/Masterbot --skill sherpa-onnx-tts-zentin-l
Please help me install this Agent Skill. Skill: sherpa-onnx-tts Source: https://github.com/Zentin-L/Masterbot/tree/main/skills/sherpa-onnx-tts Command: npx skills add https://github.com/Zentin-L/Masterbot --skill sherpa-onnx-tts-zentin-l
Private, on-device text-to-speech that doesn't rely on cloud services, enabling offline voice generation.
Run the sherpa-onnx-tts wrapper to synthesize speech from text on your machine.
High-intent search queries and answers about installing and using this skill.
Offline text-to-speech generation can be run locally by using the sherpa-onnx runtime to synthesize speech from text on your machine. This private on-device approach completely replaces cloud-based TTS workflows.
Yes, on-device voice synthesis works across macOS, Linux, and Windows. The setup requires minimal dependencies and uses local TTS via the sherpa-onnx runtime to generate speech offline.
Local TTS setup requires configuring the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables. The SKILL.md file provides instructions for runtime and model downloads needed for on-device speech synthesis.
Private on-device speech synthesis is ideal for on-device accessibility, embedded assistants, and offline narration. It provides local voice generation for applications like accessible reading and demo voices without relying on cloud connectivity.
On-device voice synthesis generates speech locally using the sherpa-onnx runtime, ensuring privacy and offline capability. Cloud-based TTS workflows rely on remote servers, whereas this approach keeps all voice generation private on your machine.
MaxSaietsGenerate speech from text offline using sherpa-onnx runtime and voice models.
jason9693Convert input text into natural ElevenLabs TTS audio for local playback.
Justicegaines03Generate speech audio files locally with sherpa-onnx and voice models.
Moshe-shipSynthesizes Saudi Arabic speech from text using NAMAA-Saudi-TTS, Lahajati, or Voxtral/Mistral TTS with optional voice cloning.
