sherpa-onnx-ttsLocal text-to-speech via sherpa-onnx (offline, no cloud)
Install via ClawdBot CLI:
clawdbot install danielsinewe/sherpa-onnx-ttsGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.12.23/sherpa-onnx-v1.Audited Apr 16, 2026 · audit v1.0
Generated Apr 22, 2026
A publisher uses offline TTS to convert text manuscripts into high-quality audiobooks without cloud dependency, ensuring privacy and low latency.
A call center integrates local TTS into its interactive voice response system to dynamically read account details or FAQs, reducing cloud costs and improving response time.
An accessibility app leverages offline TTS to read screen content, emails, or documents aloud, providing reliable speech synthesis even without internet connectivity.
An educational platform uses TTS to generate natural-sounding speech examples for learners to mimic, supporting offline use in classrooms or remote areas.
A smart home hub uses local TTS to announce weather updates, alarms, or notifications privately without sending audio data to the cloud.
Offer a free basic voice model with subscription tiers for premium, high-quality voices or additional language packs.
License the skill to enterprises needing offline, private TTS for internal applications like training modules or customer communications.
Provide a self-hosted API that charges per character synthesized, targeting developers who need scalable TTS without cloud costs.
💬 Integration Tip
Set environment variables SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR before running the wrapper; ensure model directory contains the correct .onnx and tokens files.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch contro...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...