Getting Started

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.

Caption Every Word Without Lifting a Finger

Getting subtitles onto your videos used to mean hours of rewinding, typing, and syncing timestamps by hand. This skill eliminates all of that. Paste in your video transcript, drop in a script with timing cues, or describe your footage — and get properly formatted, time-synced subtitle text ready to drop into any editing tool or video platform.

The free-auto-subtitle-generator is built for people who publish regularly and can't afford to spend half their day on captions. Whether you're subtitling a YouTube tutorial, adding accessibility text to a training video, or captioning short-form content for Instagram Reels or TikTok, this skill handles the formatting logic so you don't have to.

You get clean subtitle blocks with accurate line breaks, readable character limits per line, and proper timing intervals — the kind of output that actually looks professional on screen. No bloated software, no subscription wall, just subtitles that work.

Routing Captions to the Right Engine

When you submit a video for auto-captioning, your request is parsed for language, audio quality, and file format, then routed to the optimal speech-to-text transcription pipeline for fastest subtitle generation.

Cloud Transcription API Reference

The backend leverages a distributed cloud ASR (Automatic Speech Recognition) engine that processes audio streams frame-by-frame, generating time-coded SRT or VTT subtitle files without any manual input. Transcription jobs run asynchronously, so large video files are chunked and processed in parallel to minimize turnaround time.

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

• X-Skill-Source: free-auto-subtitle-generator
• 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

Best Practices for Auto Subtitle Generation

For the most accurate subtitle output, provide a clean transcript with speaker cues removed and filler words (um, uh) trimmed unless you specifically want them included. The cleaner your input text, the tighter your subtitle timing and line breaks will be.

Aim for subtitle blocks of 1-2 lines with no more than 42 characters per line — this keeps captions readable on both mobile and desktop screens. If you're targeting vertical video platforms like TikTok or Instagram Reels, request shorter blocks (under 32 characters) so text doesn't crowd the frame.

Always specify your video's total duration when providing a transcript without timestamps. This lets the free-auto-subtitle-generator distribute cues evenly and avoid awkward gaps or rushed text on screen.

Use Cases for the Free Auto Subtitle Generator

Content creators use this skill to caption YouTube videos, podcast clips, and course recordings without hiring a transcription service. A single long-form video that might take 3 hours to caption manually can be formatted in minutes.

Educators and corporate trainers rely on auto-generated subtitles to meet accessibility requirements for learners with hearing impairments or those watching in noisy environments. Accurate captions also improve comprehension for non-native speakers.

Social media managers use the free-auto-subtitle-generator to repurpose interview clips, product walkthroughs, and event highlights into captioned short-form content. Captions on social video increase average watch time significantly — most viewers scroll with sound off.

Filmmakers and video editors use it to generate a working SRT draft that they can fine-tune in Premiere Pro, DaVinci Resolve, or CapCut, saving hours on the initial formatting pass.

Troubleshooting Common Subtitle Issues

If your subtitle blocks are too long or run off-screen, specify a maximum character-per-line limit in your request (e.g., 'keep each line under 40 characters'). The generator will re-wrap the text accordingly.

If timestamps feel off or captions appear out of sync after importing your SRT file, check that your video editor's frame rate matches the timing format used. Mention your frame rate (24fps, 30fps, etc.) when requesting timed output for better accuracy.

For videos with heavy accents, technical jargon, or overlapping speakers, provide the transcript manually rather than relying on auto-transcription from another tool. Feeding clean, corrected text into the free-auto-subtitle-generator always produces better subtitle quality than passing through a noisy transcript.

If subtitle cues are merging or splitting at odd places, ask for a re-format with explicit sentence-boundary breaks — the skill can restructure blocks to align with natural speech pauses.