sttTranscreve arquivos de áudio em português brasileiro para texto, suportando vários formatos e incluindo timestamps.
Install via ClawdBot CLI:
clawdbot install Bohnwuks/sttGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://download.pytorch.org/whl/cu118Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Transcribes voice messages from customer support channels like WhatsApp or voice recordings, converting them to text for easier analysis and response tracking. Useful for logging complaints or inquiries in CRM systems.
Processes audio recordings of lectures or classes in formats like MP3 or M4A, generating text transcripts with timestamps for students to review or for accessibility purposes.
Transcribes audio from podcasts, videos, or interviews in Portuguese (Brazil) to create accurate subtitles or closed captions, enhancing content accessibility and SEO.
Converts audio recordings of legal depositions or meetings into text documents with timestamps, aiding in evidence organization and case preparation for law firms.
Transcribes voice notes from healthcare professionals describing patient interactions or symptoms, streamlining medical record-keeping and improving data accuracy.
Offers monthly or annual subscriptions for unlimited or tiered audio transcription, targeting businesses needing regular processing of voice messages or recordings. Revenue comes from recurring fees based on usage volume.
Provides an API that charges per minute of audio transcribed, allowing developers to integrate the skill into their apps or platforms. Revenue is generated from API calls made by third-party users.
Sells customized licenses to enterprises in industries like legal or healthcare, including features like batch processing and compliance support. Revenue comes from one-time or annual licensing fees.
💬 Integration Tip
Ensure FFmpeg is installed and inbound folder paths are correctly configured to avoid processing errors.
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.
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...