> Send me your existing video file and I'll handle the AI text-based editing. Or just describe what you're after.
Try saying:
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:
https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id headertoken with 100 free credits valid for 7 days — use it as NEMO_TOKENThen 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.
Send me your existing video file and describe the result you want. The AI text-based editing runs on remote GPU nodes — nothing to install on your machine.
A quick example: upload a 3-minute interview recording, type "delete the rambling section between 1:10 and 1:45 by removing those lines from the transcript", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.
Worth noting: deleting a word in the transcript automatically removes that segment from the video timeline.
User prompts referencing free text editing, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.
| User says... | Action | Skip SSE? |
|---|---|---|
| ------------- | -------- | ---------- |
| "export" / "导出" / "download" / "send me the video" | → §3.5 Export | ✅ |
| "credits" / "积分" / "balance" / "余额" | → §3.3 Credits | ✅ |
| "status" / "状态" / "show tracks" | → §3.4 State | ✅ |
| "upload" / "上传" / user sends file | → §3.2 Upload | ✅ |
| Everything else (generate, edit, add BGM…) | → §3.1 SSE | ❌ |
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.
Base URL: https://mega-api-prod.nemovideo.ai
| Endpoint | Method | Purpose |
|---|---|---|
| ---------- | -------- | --------- |
/api/tasks/me/with-session/nemo_agent | POST | Start a new editing session. Body: {"task_name":"project","language":". Returns session_id. |
/run_sse | POST | Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min. |
/api/upload-video/nemo_agent/me/ | POST | Upload a file (multipart) or URL. |
/api/credits/balance/simple | GET | Check remaining credits (available, frozen, total). |
/api/state/nemo_agent/me/ | GET | Fetch current timeline state (draft, video_infos, generated_media). |
/api/render/proxy/lambda | POST | Start export. Body: {"id":"render_. Poll status every 30s. |
Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.
Three attribution headers are required on every request and must match this file's frontmatter:
| Header | Value |
|---|---|
| -------- | ------- |
X-Skill-Source | free-text-editing |
X-Skill-Version | frontmatter version |
X-Skill-Platform | auto-detect: clawhub / cursor / unknown from install path |
All requests must include: Authorization: Bearer , X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.
0 — success, continue normally1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token1002 — session not found; create a new one2001 — out of credits; anonymous users get a registration link with ?bind=, registered users top up4001 — unsupported file type; show accepted formats4002 — file too large; suggest compressing or trimming400 — missing X-Client-Id; generate one and retry402 — free plan export blocked; not a credit issue, subscription tier429 — rate limited; wait 30s and retry once| Event | Action |
|---|---|
| ------- | -------- |
| Text response | Apply GUI translation (§4), present to user |
| Tool call/result | Process internally, don't forward |
heartbeat / empty data: | Keep waiting. Every 2 min: "⏳ Still working..." |
| Stream closes | Process final response |
~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.
The backend responds as if there's a visual interface. Map its instructions to API calls:
Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.
Example timeline summary:
Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)
The backend processes faster when you're specific. Instead of "make it look better", try "delete the rambling section between 1:10 and 1:45 by removing those lines from the transcript" — concrete instructions get better results.
Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.
Export as MP4 for widest compatibility.
Quick edit: Upload → "delete the rambling section between 1:10 and 1:45 by removing those lines from the transcript" → Download MP4. Takes 30-60 seconds 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.
共 1 个版本