Generate offline speech audio from text using sherpa-onnx.
npx skills add https://github.com/openaeon/OpenAEON --skill sherpa-onnx-tts-openaeon
Please help me install this Agent Skill. Skill: sherpa-onnx-tts Source: https://github.com/openaeon/OpenAEON/tree/main/skills/sherpa-onnx-tts Command: npx skills add https://github.com/openaeon/OpenAEON --skill sherpa-onnx-tts-openaeon
It solves the problem of producing text-to-speech audio without relying on cloud services or external APIs.
Set SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR in your openaeon.json for the sherpa-onnx-tts skill, then run: {baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."
High-intent search queries and answers about installing and using this skill.
You can generate speech from text offline using local TTS by running the sherpa-onnx engine directly on your machine, which synthesizes audio into a WAV file without relying on cloud services or external APIs.
Local speech synthesis with sherpa-onnx requires setting SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR, while SHERPA_ONNX_MODEL_FILE, TOKENS_FILE, and DATA_DIR are optional overrides for configuring your voice model.
Offline text to speech works for deterministic voice rendering in automated workflows by validating model artifacts locally before invoking the sherpa-onnx CLI, ensuring consistent on-device audio generation.
You can use the ONNX runtime for text to speech without an internet connection because the sherpa-onnx engine operates entirely offline, validating local model artifacts to produce audio files independently.
The best way to configure voice models for offline audio generation is to define runtime and model directories in your configuration file, allowing optional model, token, and data file overrides to select specific voices.
Offline TTS fails before invoking the sherpa-onnx CLI when required model artifacts are missing or environment variables like SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR are not properly configured.
PolealphaGenerate offline speech audio as WAV files using sherpa-onnx TTS.
adiytharpansaConvert written text into expressive speech using ElevenLabs text-to-speech.
kcns008Generates offline text-to-speech audio from plain text using sherpa-onnx runtime and voice models.
chebizarroGenerate speech audio from text using sherpa-onnx with local voice models.
