skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

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

Updated Mar 7, 2026
Search Tags:#text-to-speech#speech synthesis#sherpa-onnx#local inference#offline tts#wav audio#piper voice
One-click install
npx skills add https://github.com/shalevamin/Tau_agent --skill sherpa-onnx-tts-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/shalevamin/Tau_agent --skill sherpa-onnx-tts-shalevamin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It converts text into spoken audio locally without sending data to cloud TTS services, which is useful when you need offline operation, privacy, or no per-request API costs. ## Core Features & Use Cases - Offline Text-to-Speech: Runs the sherpa-onnx CLI locally to synthesize WAV audio from any input text. - Cross-Platform Runtime: Provides prebuilt runtime downloads for macOS, Linux, and Windows plus a Piper voice model. - Configurable Voices: Supports swapping voice models and overriding tokens or data directories via environment variables or CLI flags. - Use Case: A developer building a voice assistant on a laptop without internet access can generate spoken responses as WAV files entirely on-device. ## Quick Start Use the sherpa-onnx-tts skill to convert the text "Hello from local TTS" into a WAV audio file on my machine.

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 Piper voice model to synthesize speech entirely on-device. After downloading the runtime and model, run the wrapper with an output path and your text to produce a WAV file.

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.

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

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

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

This happens when the model directory contains multiple .onnx files or the environment variables are unset. Set SHERPA_ONNX_MODEL_FILE explicitly or pass --model-file, --tokens-file, or --data-dir to override the defaults.

Does sherpa-onnx TTS work on Windows?▼

Yes, a Windows x64 runtime download is provided. On Windows, invoke the wrapper through node with the full path, for example node {baseDir}\bin\sherpa-onnx-tts -o tts.wav followed by your text.

Related Skills

Explore More Software Engineering Skills→
bishwasherebishwashere
2

Speech

Transcribe audio to text with Whisper and synthesize speech with 11Labs.

Community
Intermediate
bachdyonbachdyon

video-audio-extractor

Extract audio streams from video files as WAV or MP3.

Community
Intermediate
FutureAtomsFutureAtoms
1

personaplex-react-native-integration

Integrate PersonaPlex AI into React Native apps with WebSocket voice conversations.

Community
Advanced
GeneralReasoningGeneralReasoning
4

openai-tts

Convert text into speech using OpenAI's TTS API with configurable voices and models.

Official
Advanced