Loading...
Loading...
Found 69 Skills
Transcribe audio with StepFun's stepaudio-2.5-asr — an SSE endpoint (NOT /v1/audio/transcriptions) with 32K context, ~85-101x RTF on long audio, and a single-call ceiling around 30 minutes (no client-side chunking). Use when transcribing Chinese / English audio with StepFun, when long-form recordings (5-30 min) need to land in one request, when migrating from step-asr / step-asr-1.1, or when hitting the misleading `model stepaudio-2.5-asr not supported` error (which actually means wrong endpoint). Triggers on 阶跃 ASR, StepFun ASR, stepaudio-2.5-asr, 转录, 语音识别, 长音频转写, 语音转文字. For TTS with the sibling stepaudio-2.5-tts model, use the stepfun-tts skill instead.
Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, live captions, or duplex voice agents.
Minimal realtime ASR smoke test for Model Studio Qwen ASR Realtime.
Volcano Engine audio/video transcription + automatic rough cut for talking-head videos. Used for speech-to-text, video-to-text, audio recognition, timestamp/SRT subtitle generation, and also for editing talking-head videos, automatic rough cutting, removing repeats, pauses, and verbal stumbles, and generating rough-cut MP4s. Trigger scenarios: when the user says "help me transcribe this video", "audio/video to text", "recognize this audio", "help me edit this talking-head video", or "auto edit".
Vox single-entry voice orchestration skill. Used to complete environment guarding, CLI installation, on-demand model download, ASR transcription, voice cloning, pipeline execution and task troubleshooting through natural language. It is used when users only describe the target without providing specific commands.
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Extract, transcribe, and translate YouTube video transcripts using the YouTubeTranscript.dev V2 API. Supports captions, ASR audio transcription, batch processing (up to 100 videos), translation to 100+ languages, and multiple output formats. Use when working with YouTube videos, subtitles, captions, or video-to-text conversion.
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps, summaries, or answering questions about video content. Automatically selects the best available provider based on configured API keys - prefers full video understanding (Gemini/OpenRouter) over ASR-only providers. Supports model selection per provider.
Professional-level refinement and verification for Chinese SRT subtitles for launch. Used to clean ASR-based raw subtitles into a publishable version, only performing subtitle-level cleaning and correction without formal rewriting, summarization, or expansion; meanwhile, strictly maintaining synchronization with the original audio, splitting entries only within the original subtitle time range when necessary, outputting a complete clean SRT, and then using the accompanying verification script for final rule checks and timeline review. Suitable for tasks such as documentaries, interviews, oral broadcasts, screen recordings that require correcting recognition errors, deleting meaningless filler words, adding pause spaces, limiting single-entry word count, and avoiding accidental deletion of meaningful subtitles.
Create short-video subtitles with Luma / 拾光 / 拾光工具. Use ASR, segmentation, styling, and burn-in as composable steps; keep editorial decisions in the agent instructions.
Process WeChat Channels share links, extract OCR/ASR note materials and generate Markdown notes.