Themed Avatar Video Creator - Confirm & Copy Final Agent Code

Describe

Describe your task

Refine

Refine the plan

SubAgents

Review all agents

Deploy

Deploy your agent

Review Final Agent Copy

Expand

[
  {
    "taskID": 171,
    "semanticTitleOfTask": "Generate a friendly, engaging voice-over script based on the user's topic",
    "taskDescription": "This task uses Skill #171 to create a natural-sounding voice-over script (100–300 words) from the user's topic. It ensures a friendly tone, easy flow, clear structure, and includes a hook and conclusion to keep the audience engaged and interested.",
    "inputDescription": "This task requires the user's topic description (VARIABLE1), a brief text prompt specifying the theme or guidelines of the script. The scriptwriter skill uses this input to tailor the content, tone, and structure of the resulting voice-over script.",
    "inputRequired": ["VARIABLE1"],
    "outputDescription": "A text script between 100–300 words in length, phrased in a conversational and naturally-flowing style. It will include a short introduction to hook the audience, a cohesive body with smooth transitions, and a concluding statement or call-to-action.",
    "outputName": "script_text_171",
    "promptInstruction": "You are a professional script writer. Create a conversational, naturally-flowing script (100–300 words) about {variable1} for a voice-over narration. Use a friendly, engaging tone, avoid complex jargon, include a hook, conclusion or call-to-action, and structure the script clearly with natural rhythm and flow for spoken delivery."
  },
  {
    "taskID": 170,
    "semanticTitleOfTask": "Turn Script Text into Voice Over MP3 Audio",
    "taskDescription": "This single-step subagent uses a text-to-speech engine to convert the input script text (about 100–300 words) into a natural-sounding voice over in MP3 format.",
    "inputDescription": "One input is required: the script text to be converted. The text will be processed by a text-to-speech module to produce a voice-over MP3 file.",
    "inputRequired": ["script_text_171"],
    "outputDescription": "A single URL pointing to the generated MP3 file containing the narrated script, enabling easy playback of the voice over track.",
    "outputName": "voiceover_file_170",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate themed 16:9 avatar image",
    "taskDescription": "This task takes the user's avatar description and produces a high-quality 16:9 PNG image with a photorealistic headshot/upper body framing for use as a talking head avatar.",
    "inputDescription": "One input: 'VARIABLE2' which is the user's description of the desired avatar subject (e.g., 'woman wearing a Christmas hat in a department store').",
    "inputRequired": ["VARIABLE2"],
    "outputDescription": "A single URL pointing to the newly generated 16:9 PNG avatar image, suitable for talking head video use.",
    "outputName": "avatar_image_222",
    "promptInstruction": "Use skill #222 to generate a professional, photorealistic 16:9 PNG avatar based on user description. Frame the subject as a headshot or upper body shot, center the face under well-lit, natural lighting conditions. Background should be contextually appropriate and slightly defocused. Output should be high resolution with natural proportions, suitable for a talking head video and natural lip synchronization."
  },
  {
    "taskID": 168,
    "semanticTitleOfTask": "Generate Lip-Synced Talking Head Video",
    "taskDescription": "This task combines a static avatar image, a user-provided MP3 voiceover, and the transcript text to produce a lip-synced talking head MP4 video. The skill loads the avatar image, processes the audio, and uses the transcript to synchronize lip movements, rendering the final animated output.",
    "inputDescription": "Three inputs are required: the MP3 URL for the voiceover, the text transcript used for lip-sync alignment, and the PNG URL of the themed avatar image. These inputs are processed together to create the final talking head animation.",
    "inputRequired": ["voiceover_file_170", "script_text_171", "avatar_image_222"],
    "outputDescription": "The output is a single MP4 video file URL containing a lip-synced animation of the static avatar, speaking the provided script in sync with the audio.",
    "outputName": "talking_head_video_168",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 501,
    "semanticTitleOfTask": "LLM - Generate short script based on user topic",
    "taskDescription": "This task creates a short, conversational script of approximately 100–300 words from the user’s topic. The script will be used in a voice-over recording for the final video.",
    "inputDescription": "One input: the user’s textual description or topic that the script should focus on.",
    "inputRequired": ["VARIABLE1"],
    "outputDescription": "A concise text script with an introduction, body, and conclusion, suitable for voice narration.",
    "outputName": "script_text_501",
    "promptInstruction": "You are a professional script writer for short-form video content. Create a natural, engaging script about `VARIABLE1`. The script should be conversational in tone, between 100-300 words, and structured with a clear introduction, body, and conclusion. Avoid complex jargon and write in a way that would sound natural when spoken aloud. Format the output as plain text without any special characters or formatting."
  },
  {
    "taskID": 502,
    "semanticTitleOfTask": "Convert script to voice-over MP3",
    "taskDescription": "This task takes the script text and generates a spoken narration in MP3 format using a text-to-speech engine.",
    "inputDescription": "One input: the text script from the previous task (script_text_501).",
    "inputRequired": ["script_text_501"],
    "outputDescription": "A generated MP3 file URL containing the voice narration of the script.",
    "outputName": "voiceover_file_502",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 503,
    "semanticTitleOfTask": "Generate a topical AI avatar image",
    "taskDescription": "This task creates a photorealistic headshot image based on the user’s avatar description, ensuring a suitable front-facing pose with neutral expression and simple background.",
    "inputDescription": "One input: a textual description specifying the appearance and context for the avatar (e.g., 'woman wearing a Christmas hat in a department store').",
    "inputRequired": ["VARIABLE2"],
    "outputDescription": "A high-quality PNG image URL that can be used as the talking head avatar in the final video.",
    "outputName": "avatar_image_503",
    "promptInstruction": "Generate a high-quality, photorealistic headshot image of `VARIABLE2`. The image should be front-facing, well-lit, and suitable for use as a talking head avatar. Ensure the background is simple and non-distracting. The subject should have a neutral, pleasant expression and be looking directly at the camera. Generate the image with dimensions 1024x1024 pixels."
  },
  {
    "taskID": 504,
    "semanticTitleOfTask": "Synthesize final talking head video",
    "taskDescription": "This task combines the generated avatar image, the voice-over MP3, and the script text to produce a lip-synced talking head MP4 video.",
    "inputDescription": "Three inputs: the MP3 file URL of the narration, the script text for lip-sync alignment, and the PNG avatar image URL.",
    "inputRequired": ["voiceover_file_502", "script_text_501", "avatar_image_503"],
    "outputDescription": "A final MP4 video URL featuring the custom AI avatar speaking the script with aligned lip-sync.",
    "outputName": "talking_head_video_504",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 601,
    "semanticTitleOfTask": "Generate a concise, eye-catching video title from final script",
    "taskDescription": "This task uses a language model to create an attention-grabbing title based on the final script. It should reflect the core theme, be memorable, and entice viewers to watch.",
    "inputDescription": "Requires the final script text of the video. The script provides context on the topic, tone, and key points, which the language model will use to craft a catchy title.",
    "inputRequired": ["script_text_171"],
    "outputDescription": "A short, appealing title (5-10 words) that accurately portrays the video's main topic and piques viewer interest",
    "outputName": "video_title_601",
    "promptInstruction": "You are a marketing copywriter skilled at generating concise, engaging titles. Read the final script text and produce a brief, memorable title that captures the main subject, entices viewers to watch, and fits well for an online video platform."
  },
  {
    "taskID": 602,
    "semanticTitleOfTask": "Write an engaging video description for platform optimization",
    "taskDescription": "This task uses a language model to create a viewer-friendly description for the final video. It provides context, covers main talking points, and includes relevant keywords or calls to action to encourage engagement.",
    "inputDescription": "Requires the final script text of the video so the language model can identify the main topics, intended audience, and relevant details to include in the description.",
    "inputRequired": ["script_text_171"],
    "outputDescription": "A clear, SEO-friendly description (50-150 words) outlining the video's purpose, main points, and any relevant links or information",
    "outputName": "video_description_602",
    "promptInstruction": "Draft a compelling video description that briefly summarizes the main content of the final script. Include keywords to boost visibility, a short call to action, and any necessary references or links. Keep the tone friendly and inviting."
  },
  {
    "taskID": 603,
    "semanticTitleOfTask": "Suggest SEO tags for better video discoverability",
    "taskDescription": "This task uses a language model to identify and suggest relevant tags or keywords from the script, boosting the video's visibility on platforms like YouTube or search engines.",
    "inputDescription": "Requires the final script text of the video for semantic analysis. The language model examines key themes and topics to determine popular, relevant search terms.",
    "inputRequired": ["script_text_171"],
    "outputDescription": "An array of 5-15 targeted keywords or tags to help the video rank higher in searches",
    "outputName": "video_tags_603",
    "promptInstruction": "Extract several relevant tags or short phrases that reflect the video's central topics and appeal to the target audience. Make sure the tags are popular search terms and accurately connected to the script's main points."
  }
]

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD