Saltar al contenido
TakoAPI
Volver a skills

anima

por hmyaoyuan

Coding Agents & IDEs
1.2kDescargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Anima Avatar - Interactive Video Generation Engine.

Descripción

Qué hace esta skill

Generates 16:9 avatar videos where a character sprite speaks scripted text with emotion-matched expressions and synthesized voice. Combines Fish Audio for TTS, a library of 30+ character sprites auto-selected by emotion tag, and FFmpeg for frame-by-frame video composition. Finished videos can be uploaded directly to Feishu as native media or saved locally in preview mode.

Handles TTS generation, emotion-based sprite selection, parallel frame rendering, audio sync, and video encoding in one pipeline instead of requiring separate tools for each step.

Cuándo usarla

  • Sending an animated character announcement to a Feishu group chat
  • Generating a multi-scene explainer video from a JSON script
  • Producing a custom-voiced avatar response for a chatbot reply
  • Batch-creating onboarding video clips with a branded character
  • Previewing a scripted dialogue locally without uploading anywhere

Flujo de trabajo de ejemplo

ENTRADA

User asks: Generate a video where the character says 'Good morning team!' happily and then says 'Please review the report' with a thinking expression, and send it to Feishu user ou_abc123

AGENTE
  1. 1

    Parses the request into a two-scene script: [{"text":"Good morning team!","emotion":"Happy"},{"text":"Please review the report","emotion":"Think"}]

  2. 2

    Calls Fish Audio API to synthesize audio for each line using the configured voice model

  3. 3

    Selects matching sprites from the library based on emotion tags (Happy, Think)

  4. 4

    Renders video frames using sharp and SVG text overlay, then composes the final MP4 with FFmpeg

  5. 5

    Uploads the finished video to the specified Feishu user via send_video_pro.js

SALIDA

A 16:9 MP4 video delivered to the Feishu conversation with correct duration and native playback

Requisitos

  • Fish Audio API key (FISH_AUDIO_KEY) — sign up at fish.audio/dashboard/api
  • Fish Audio voice model reference ID (FISH_AUDIO_REF_ID) — from your Fish Audio account
  • Google Gemini API key (GEMINI_API_KEY) — optional, needed only for sprite generation, get at aistudio.google.com/apikey
  • Feishu app ID and secret (FEISHU_APP_ID, FEISHU_APP_SECRET) — optional, needed only for Feishu delivery
  • ffmpeg installed on the system

Instalación

clawhub install hmyaoyuan/anima

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces