skills.rest
JEROME-PRAKASH-L
JEROME-PRAKASH-LCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sherpa-onnx-tts

Generates speech audio from text using the offline sherpa-onnx TTS engine.

1|Updated Jun 9, 2026
Search Tags:#text-to-speech#voice synthesis#sherpa-onnx#piper#local ai#offline tts#wav audio
One-click install
npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill sherpa-onnx-tts-jerome-prakash-l
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/JEROME-PRAKASH-L/openclaw/tree/main/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill sherpa-onnx-tts-jerome-prakash-l

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It provides local text-to-speech synthesis without sending text to cloud APIs, producing WAV audio files entirely on your own machine across macOS, Linux, and Windows. ## Core Features & Use Cases - Offline Speech Synthesis: Converts text into WAV audio using the sherpa-onnx CLI with VITS/Piper voice models, requiring no network connection at runtime. - Cross-Platform Runtime Downloads: Automates downloading the correct sherpa-onnx runtime binary for macOS, Linux x64, or Windows x64, plus a default English voice model. - Configurable Voices: Supports swapping in any model from the sherpa-onnx tts-models release and overriding model, tokens, and data files via environment variables or CLI flags. - Use Case: A user wants their assistant to speak replies aloud on a laptop without a cloud TTS subscription; this Skill downloads the runtime and voice model, then synthesizes 'Hello from local TTS.' into a playable WAV file. ## Quick Start Ask the assistant to install the sherpa-onnx runtime and voice model, then convert the phrase 'Hello from local TTS' into a WAV audio file.

Frequently Asked Questions about sherpa-onnx-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech locally without a cloud API?▼

Use the sherpa-onnx offline TTS CLI with a VITS/Piper voice model to synthesize text into a WAV file entirely on your machine. Run the wrapper with an output path and your text, for example producing tts.wav from a sentence.

How do I install sherpa-onnx TTS on macOS, Linux, or Windows?▼

Download the platform-specific sherpa-onnx runtime archive and a voice model, extract them into the tools directory, then set SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR in the OpenClaw config. On Windows, invoke the wrapper through node.

Can I use a different voice model with sherpa-onnx TTS?▼

Yes, you can download any model from the sherpa-onnx tts-models release and point SHERPA_ONNX_MODEL_DIR at it. If the model directory contains multiple .onnx files, set SHERPA_ONNX_MODEL_FILE or pass --model-file to select one.

Does sherpa-onnx TTS require an internet connection to synthesize speech?▼

No, synthesis runs fully offline once the runtime and voice model are downloaded. Internet access is only needed for the initial download of the runtime binaries and model files.

Why does sherpa-onnx TTS fail to find the model files?▼

This happens when SHERPA_ONNX_MODEL_DIR points to the wrong path or the model archive was not extracted correctly. Verify the directory contains the .onnx model and tokens files, or pass --tokens-file and --data-dir explicitly.

Related Skills

Explore More Software Engineering Skills→
yazelinyazelin
31

voice

Convert voice messages to text and generate spoken responses.

Community
Intermediate
opensquillaopensquilla
6.8k

audio-cog

Generate webpage narration audio as WAV files via OpenRouter audio models.

Official
Advanced
refly-airefly-ai
199

fish-audio

Generate speech, transcribe audio, and create voice narration with Fish Audio models.

Official
Intermediate
framerslabframerslab

google-cloud-tts

Synthesize text to MP3 speech via the Google Cloud Text-to-Speech API.

Official
Intermediate