salute-speechTranscribe audio files using Sber Salute Speech async API. Russian-first STT with support for ru-RU, en-US, kk-KZ, ky-KG, uz-UZ.
Install via ClawdBot CLI:
clawdbot install chorus12/salute-speechGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
upload → https://smartspeech.sber.ru/rest/v1/data:uploadCalls external URL not in known-safe list
https://developers.sber.ru/studio/Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Transcribes internal corporate meetings recorded in Russian or English to create searchable, timestamped minutes. Useful for compliance, knowledge retention, and enabling team members to review discussions without listening to full recordings.
Processes recorded customer support calls in Russian or Kazakh to generate transcripts for quality assurance, training, and sentiment analysis. The callcenter model optimizes for telephony audio, helping identify common issues and agent performance.
Converts recorded university lectures or online courses in Russian, English, or Central Asian languages into text with timestamps. Facilitates note-taking, accessibility for hearing-impaired students, and content indexing for e-learning platforms.
Transcribes audio from podcasts, interviews, or video content in supported languages to create subtitle files or scripts. Reduces manual transcription time for media producers and broadcasters, especially for Russian-language content.
Handles audio recordings from public hearings, administrative proceedings, or multilingual community interactions in languages like Kyrgyz or Uzbek. Ensures accurate, timestamped records for transparency, legal documentation, and archival purposes.
Offer a web-based platform where users upload audio files for automated transcription using this skill. Charge per minute of audio processed or via subscription tiers, targeting businesses needing regular transcription like law firms or media companies.
Provide custom integration of this skill into existing enterprise systems (e.g., CRM, learning management systems) for automated transcription workflows. Revenue comes from one-time setup fees and ongoing support contracts, focusing on industries with high audio data volume.
Resell access to the transcription API bundled with additional features like analytics or multi-language support. White-label the service for other tech companies or agencies, generating revenue through API usage fees and partnership agreements.
💬 Integration Tip
Ensure the SALUTE_AUTH_DATA environment variable is securely set with a valid API key, and adjust --max-wait-time for files longer than 1 hour to avoid timeout errors during async processing.
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...