skills.rest
srgaba
srgabaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sherpa-onnx-tts

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

Updated Mar 30, 2026
Search Tags:#text-to-speech#speech synthesis#wav#sherpa-onnx#piper#offline tts#voice model
One-click install
npx skills add https://github.com/srgaba/open-claw --skill sherpa-onnx-tts-srgaba
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/srgaba/open-claw/tree/main/project/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/srgaba/open-claw --skill sherpa-onnx-tts-srgaba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It converts text into spoken audio entirely on your local machine, removing the need for cloud TTS APIs, network access, or per-request fees. ## Core Features & Use Cases - Offline Text-to-Speech: Synthesizes WAV audio from text using the sherpa-onnx CLI with VITS/Piper voice models. - Cross-Platform Runtime: Provides prebuilt runtime downloads for macOS, Linux, and Windows, plus a downloadable en_US voice model. - Configurable Voices: Supports swapping voice models and overriding tokens, model files, or data directories via flags or environment variables. - Use Case: Generate a voiceover for a demo video by running the wrapper script with your script text, producing a local WAV file without sending data to any external service. ## Quick Start Ask the assistant to convert the text "Hello from local TTS" into a speech audio file saved as tts.wav using the local sherpa-onnx voice.

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 offline without a cloud API?▼

Use the sherpa-onnx CLI with a local VITS/Piper voice model to synthesize speech entirely on your machine. Run the wrapper with an output path and your text, for example producing a tts.wav file, with no network calls involved.

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

Download the prebuilt sherpa-onnx runtime archive for your OS and extract it into the runtime directory, then download a voice model into the models directory. Set SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR in your configuration before running.

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

Yes, you can download any compatible 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.

Why does sherpa-onnx TTS fail when the model directory has multiple .onnx files?▼

The engine cannot determine which model file to load when several .onnx files exist in the model directory. Resolve it by setting the SHERPA_ONNX_MODEL_FILE environment variable or passing the --model-file flag with the exact file.

Does sherpa-onnx TTS work on Windows?▼

Yes, a Windows x64 runtime build is available for download. On Windows, invoke the wrapper through node, for example node bin\sherpa-onnx-tts -o tts.wav followed by your text.

Related Skills

Explore More Software Engineering Skills→
Buntyarora97Buntyarora97

podcast-generator

Convert text-based content into podcast scripts and audio via ElevenLabs.

Community
Advanced
swyxioswyxio
154

podcast-publishing-assistant

Transcribe long-form audio and generate publishing assets with chapter markers.

Community
Intermediate
chebizarrochebizarro

sag

Convert text to speech via the ElevenLabs API with a command-line interface.

Community
Intermediate
dioerdendioerden

sag

Convert text to spoken word using the ElevenLabs TTS service.

Community
Intermediate