Synthesize WAV audio from plain text using sherpa-onnx runtime.
npx skills add https://github.com/Yogi-076/Vajrascan.on --skill sherpa-onnx-tts-yogi-076
Please help me install this Agent Skill. Skill: sherpa-onnx-tts Source: https://github.com/Yogi-076/Vajrascan.on/tree/main/moltbot/skills/sherpa-onnx-tts Command: npx skills add https://github.com/Yogi-076/Vajrascan.on --skill sherpa-onnx-tts-yogi-076
Enables local, offline speech synthesis so users can generate high-quality audio from text without sending data to cloud services, preserving privacy and reducing latency.
Run the sherpa-onnx-tts wrapper to generate a WAV file from text, for example produce a file named tts.wav speaking the phrase "Hello from local TTS".
High-intent search queries and answers about installing and using this skill.
Offline text-to-speech synthesis generates WAV audio from plain text locally using the sherpa-onnx runtime, eliminating cloud dependency and preserving data privacy.
Local TTS synthesis requires configuring SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables to specify the sherpa-onnx runtime path and compatible voice model directory.
Offline speech synthesis runs natively on macOS, Linux, and Windows, supporting cross-platform CLI automation and on-device voice generation without internet access.
Offline TTS integration uses a wrapper added to PATH and configured via environment variables, enabling programmatic text-to-speech synthesis for scripted workflows and embedded systems.
Privacy-first text-to-speech workflows operate entirely offline without internet access, making them ideal for environments where cloud TTS is unavailable or undesirable.
Offline text-to-speech synthesis outputs WAV audio files, such as generating a file named tts.wav from the input phrase, suitable for playback and further processing.
sentientspriteGenerate speech audio files locally using sherpa-onnx and Piper TTS models.
enclawedGenerate offline WAV speech from text using sherpa-onnx runtime and local voice models.
adiytharpansaConvert spoken audio into text and executable voice commands.
lemonlqfSynthesize speech offline using sherpa-onnx runtime and voice models.
