audio-ptbr-autoreplyBrazilian Portuguese voice auto-reply skill for OpenClaw. Transcribes audio locally with wav2vec2, generates a reply with the local OpenClaw agent by default...
Install via ClawdBot CLI:
clawdbot install henrique-simoes/audio-ptbr-autoreplyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
$ANTHROPICPotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-portugueseAI Analysis
The skill accesses legitimate AI APIs (Claude, HuggingFace) for its stated purpose of voice processing and response generation. While it handles sensitive audio data, there's no evidence of unauthorized data exfiltration or hidden malicious instructions. The credential access and shell commands appear related to normal installation/configuration.
Generated May 21, 2026
Companies provide voice-based customer support in Brazilian Portuguese. Users send audio messages with questions or issues; the system transcribes them, generates an intelligent response using Claude, and replies with a natural-sounding audio message. This enables efficient, hands-free support for users who prefer speaking over typing.
Individuals use voice commands to interact with a personal assistant for tasks like setting reminders, getting weather updates, or controlling smart home devices. The assistant understands Brazilian slang and regional accents, and responds audibly with the selected neural voice.
Language learners practice speaking by sending audio messages in Portuguese. The system transcribes their speech, corrects pronunciation and grammar via Claude, and returns an audio reply with the correct version. This provides immersive, real-time feedback.
Visually impaired users interact with digital services entirely through voice. They send audio queries (e.g., banking transactions, information retrieval) and receive audio responses, leveraging the system's high-accuracy transcription and TTS capabilities.
Businesses deploy an AI-powered receptionist that handles incoming voice calls or messages. It can answer frequently asked questions, schedule appointments, or route complex queries to human staff. The system operates silently, providing only audio responses for a natural interaction.
Charge companies a monthly fee based on usage (number of audio transactions or minutes processed). Offer tiered plans with different levels of support and integration features. Revenue is recurring and scales with client size.
Provide the transcription, AI response, and TTS as a cloud API. Charge per request (e.g., per audio minute). Developers integrate the API into their own applications, generating revenue from each call.
Offer a customizable white-label version of the skill for contact centers serving Brazilian customers. Charge a one-time setup fee plus ongoing maintenance and support. The contact center brands the solution as its own.
💬 Integration Tip
For quick setup, run 'bash install.sh' and restart OpenClaw. Ensure you have at least 300MB free space for voice models.
Scored Jul 11, 2026
Audited Apr 18, 2026 · audit v1.0
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.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
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。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
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...