🎬 Text To Video Ai App — 技能工具

技能文档

Getting Started

Got text prompts to work with? Send it over and tell me what you need — I'll take care of the AI video creation.

Try saying:

• "convert a 150-word product description into a 1080p MP4"
• "turn this script into a 30-second video with visuals and background music"
• "generating videos from written scripts or text prompts for marketers, content creators, social media managers"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

# Text to Video AI App — Convert Text Into AI Videos

Drop your text prompts in the chat and tell me what you need. I'll handle the AI video creation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 150-word product description, ask for turn this script into a 30-second video with visuals and background music, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, clearer scripts produce more accurate and polished video output.

Matching Input to Actions

User prompts referencing text to video ai app, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

• Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":""}. Gives you a session_id.
• Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
• Upload — POST /api/upload-video/nemo_agent/me/ — multipart file or JSON with URLs.
• Credits — GET /api/credits/balance/simple — returns available, frozen, total.
• State — GET /api/state/nemo_agent/me//latest — current draft and media info.
• Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/ every 30s for completed status and download URL.

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

Headers are derived from this file's YAML frontmatter. X-Skill-Source is text-to-video-ai-app, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

Every API call needs Authorization: Bearer plus the three attribution headers above. If any header is missing, exports return 402.

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)

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Error Handling

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn this script into a 30-second video with visuals and background music" — concrete instructions get better results.

Max file size is 200MB. Stick to TXT, DOCX, PDF, SRT for the smoothest experience.

Export as MP4 for widest compatibility across all platforms and devices.

Common Workflows

Quick edit: Upload → "turn this script into a 30-second video with visuals and background music" → Download MP4. Takes 1-2 minutes for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.