wjs-transcribing-audioUse 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...
Install via ClawdBot CLI:
clawdbot install jianshuo/wjs-transcribing-audioGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/user/jianshuoUses known external API (expected, informational)
api.openai.comAudited Jun 5, 2026 · audit v1.0
Generated Oct 7, 2026
Podcast producers need source-language SRT files for accessibility, SEO, and YouTube uploads. This skill automatically transcribes long-form episodes, handling quiet stretches without loop hallucinations and producing readable cues on-screen.
Content teams with Spanish, French, Japanese, or other non-Chinese videos use this skill to generate accurate source SRTs before feeding them into a translation skill. Word-level timestamps and punctuation-bounded cues ensure downstream translated subtitles remain properly timed.
Educational platforms delivering Mandarin or Cantonese lectures route audio through Volcano ASR for superior Chinese accuracy. The resulting SRT enables searchable transcripts, closed captions, and student accessibility without manual transcription.
Newsrooms and documentary teams transcribe interviews with timestamped SRTs for editing, quoting, and subtitle overlays. The skill's resilience against whisper API quirks makes it practical for long, ambient recordings.
Creators and agencies transcribe TikTok, Reels, and Shorts audio into SRTs for burned-in or platform-native captions. The cue assembly recipe keeps text within character limits suited to vertical video.
Offer a web app where users upload audio/video and receive source-language SRTs, with tiered plans based on monthly minutes or priority processing. This skill powers the core transcription engine, routing Chinese to Volcano and other languages to Whisper with optimized cue assembly.
Expose an API wrapper around this skill for developers building localization, accessibility, or media pipelines. Charge per minute of audio or per API call, with volume discounts for enterprise customers.
Combine this skill with translation and dubbing services to offer end-to-end subtitle localization. Clients provide raw media and receive source SRT plus translated and burned-in versions, with human QA as an upsell.
💬 Integration Tip
Always pin the source language and use word-level timestamps instead of response_format=srt to avoid 30-second blob cues and loop hallucinations; compress audio to 64kbps mono MP3 and chunk into 10-minute pieces for reliable uploads.
Scored Oct 7, 2026
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.
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。
Generate AI text-to-speech audio, use saved voices, or create a one-shot voice clone from an HTTPS reference audio URL and exact transcript via AceDataCloud API.
Generate AI music with Producer via AceDataCloud API. Use when creating songs, generating lyrics, extending tracks, creating covers, swapping vocals/instrumentals, replacing song sections, or uploading reference audio. Supports custom lyrics, instrumental-only mode, and multiple creative actions.
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...