Getting Started

Send me your script or video brief and I'll generate a professional AI spokesperson video for you. No script yet? Just describe your topic, audience, and tone and I'll build from there.

Try saying:

• "Create a 60-second AI spokesperson video for my SaaS product launch where the presenter explains the top three features in a confident, friendly tone"
• "Generate a talking-head video script and avatar recommendation for an employee onboarding welcome message from our fictional CEO"
• "I need an AI presenter video in Spanish for our Latin American marketing campaign — professional tone, female avatar, 90 seconds max"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Your Brand's Face, Powered by AI

Creating video content that feels personal and professional has traditionally required booking talent, renting studios, and managing post-production timelines. AI spokesperson video changes that equation entirely. With this skill, you can turn a written script into a fully produced talking-head video featuring a realistic AI presenter — in minutes, not days.

The skill is designed for anyone who needs a human presence in their video without the logistics of filming. Think product explainers, onboarding walkthroughs, social media announcements, or internal communications — all delivered by an AI avatar that speaks naturally, maintains eye contact, and conveys the right tone for your audience.

Whether you're a solo entrepreneur launching a new offer or a content team producing hundreds of videos per month, this tool scales with you. You control the script, the presenter style, and the message. The AI handles everything else — from lip-sync accuracy to natural gesture and pacing — so your audience gets a polished, trustworthy presentation every time.

Avatar Request Routing Logic

When you submit a spokesperson video request — including your script, avatar selection, voice, and background — the skill parses those parameters and routes them to the appropriate AI video rendering pipeline based on avatar type and output resolution.

Cloud Rendering API Reference

AI spokesperson videos are processed entirely in the cloud, where your script is lip-synced to your chosen avatar using neural rendering engines that handle voice cloning, facial animation, and video compositing at scale. Render jobs are queued and returned as a hosted video URL or downloadable MP4 once the pipeline completes.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: ai-spokesperson-video
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

SSE Event Handling

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Handling

Common Workflows

The most frequent use case for AI spokesperson video is product marketing — specifically explainer videos where a presenter walks viewers through a feature, pricing tier, or use case. Users typically paste a landing page URL or bullet-point list and ask the skill to convert it into a presenter script, then generate avatar and scene recommendations.

Another high-volume workflow is internal communications. HR teams use this skill to produce consistent, professional onboarding videos, policy update announcements, and training module intros without scheduling filming time with executives or managers.

Educators and course creators rely on this skill to add a human face to lessons that would otherwise be screen recordings or slide decks. A talking AI presenter improves viewer retention and gives the course a more polished, credible feel.

Finally, agencies use the AI spokesperson video skill to prototype video campaigns for clients before committing to live production — validating messaging and tone with a realistic avatar stand-in before any budget is spent on real talent.

Integration Guide

Getting your AI spokesperson video from concept to published is straightforward. Start by providing your script directly in the chat — paste it in full or describe the key message points and let the skill draft it for you. You can specify avatar preferences such as gender, age range, and presentation style (formal, conversational, energetic), along with language and accent if needed.

Once the video parameters are set, the skill generates a preview-ready output that you can review and refine. Adjust pacing, swap the avatar, or revise the script in follow-up messages before finalizing. Finished videos can be exported for use in landing pages, LMS platforms, email campaigns, YouTube, or internal communication tools like Slack and Notion embeds.

For teams with existing brand assets, you can describe your brand voice, color preferences for lower-thirds or backgrounds, and any specific visual framing — the skill incorporates these into its output guidance so your videos stay on-brand across every production.