菜单
Transcribe audio or video through the PopiArt runtime baseline for local-first speech-to-text. Use this when the user wants a PopiArt-managed STT path for transcripts, captions, or analysis without manually running local scripts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Turn one source image into a short video through the PopiArt runtime baseline. Use this when the user wants the most direct image-to-video path for motion previews, short teaser clips, or runtime validation.
Convert text to speech through the PopiArt runtime baseline for multi-model TTS. Use this when the user wants one general text-to-speech entry point without handling upstream provider credentials directly.
Transform one existing image into a new image through the PopiArt runtime baseline. Use this when the user already has a source image and wants the most direct image-to-image path for redraws, style transfer, or pipeline validation.
Generate one showcase image for PopiStudio Alice with strict character consistency. Use this when a creator agent needs a single Alice proof frame, demo still, or presentation keyframe from the current Alice master reference.
Generate one image from text through the PopiArt runtime baseline. Use this when the user wants the most direct text-to-image path for smoke tests, concept frames, or simple creator-agent image generation.
Generate one short showcase video for PopiStudio Alice with strict character consistency. Use this when a creator agent needs a single Alice teaser shot, demo clip, or animated proof video from the current Alice master reference or Alice keyframe artifact.
| name | popiskill-audio-stt-local-v1 |
| description | Transcribe audio or video through the PopiArt runtime baseline for local-first speech-to-text. Use this when the user wants a PopiArt-managed STT path for transcripts, captions, or analysis without manually running local scripts. |
| tags | ["official","runtime","audio","stt","local"] |
| version | v1 |
| model_type | audio |
| estimated_duration_s | 120 |
| default_profile | true |
| profile_description | Official PopiArt runtime baseline for local-first speech-to-text transcription. |
This is an official PopiArt runtime catalog skill.
Popiart_skillhub owns the public skill definition.popiartServer owns registration, execution, jobs, artifacts, and transcript outputs.PopiNewAPI owns any managed speech-model routing that sits behind the server boundary.popiartcli owns source upload ergonomics, run, jobs, and artifact retrieval.Use it when the goal is to:
Do not use it for:
source_artifact_id, oraudio_url, orvideo_urllanguagebackendmodeldiarizationtimestampsformatpromptnotessource_artifact_id when the source clip already comes from PopiArt.audio_url or video_url only when the source already lives at a stable URL.popiart.popiart run popiskill-audio-stt-local-v1 --input @params.json --wait
Inline example:
popiart run popiskill-audio-stt-local-v1 --input '{"source_artifact_id":"art_123","language":"zh","timestamps":true}' --wait
{
"source_artifact_id": "art_123",
"language": "zh",
"backend": "auto",
"model": "default",
"diarization": false,
"timestamps": true,
"format": "text"
}
After the job finishes:
job_idtext when the runtime returns inline transcript textartifact_ids for transcript, subtitle, or segment artifactspopiart artifacts pull <artifact-id> when a local transcript file is neededpopiart artifacts upload ./clip.wav --role source.video_url is acceptable when the runtime extracts audio server-side.popiskill-audio-tts-multimodel-v1.