Audio To Text

Skip the learning curve of professional editing software. Describe what you want — transcribe this audio and add the text as captions on screen — and get cap...

Security Scan

The skill's declared purpose (cloud audio→captioning) matches most of its runtime instructions, but there are mismatches about config path access and a few instructions that ask the agent to read local skill/install metadata that aren't declared in the registry — investigate before installing or supplying credentials.

Purpose & Capability

The skill is an audio→captioning front-end that calls a remote API (mega-api-prod.nemovideo.ai). Requesting a NEMO_TOKEN is coherent with that purpose. However the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) as required metadata while the registry summary above declared no required config paths — this mismatch should be clarified.

Instruction Scope

SKILL.md instructs the agent to: use NEMO_TOKEN if present, otherwise obtain an anonymous token by POSTing to the external API (expected); read the SKILL.md file's YAML frontmatter at runtime for attribution; and detect the install path (e.g., ~/.clawhub/) to set X-Skill-Platform. Reading the skill file and detecting install path means the agent will access local files and paths. Those file reads are not inherently malicious but are broader scope than a purely network-only client and are not fully reflected in registry metadata.

Install Mechanism

No install spec or code files are present; this is instruction-only. That keeps on-disk risk low because nothing is downloaded or automatically written by an installer.

Credentials

Only one env var is declared (NEMO_TOKEN), which fits the described API usage. But the SKILL.md frontmatter declares access to a config path (~/.config/nemovideo/) which the registry metadata did not list. Access to a user config directory can expose other credentials or settings; the skill does not justify why it needs that path. Also the instructions say to 'use it as NEMO_TOKEN' for an anonymously acquired token — clarify whether tokens are stored persistently or only used ephemerally.

Persistence & Privilege

always is false and there are no instructions to modify other skills or system-wide settings. The skill can be invoked by the model (normal), and there is no install script that would persistently alter the environment.

What to consider before installing

This skill appears to do what it claims (upload audio to a remote service and return captioned video), but there are a few things to check before installing or providing credentials: - Clarify the config-path mismatch: ask the publisher whether the skill truly needs access to ~/.config/nemovideo/ and what it will read from there. The public registry metadata and SKILL.md disagree. - Prefer providing only ephemeral/anonymous tokens. If you must supply a long-lived NEMO_TOKEN, confirm the token's scope and that the backend domain (mega-api-prod.nemovideo.ai) is the official vendor endpoint. - Be aware that audio files are uploaded to a third-party service; do not send sensitive audio unless you trust the service and its privacy policy. - The skill reads its own SKILL.md frontmatter and attempts to detect install paths for attribution. If you run agents on a sensitive host, consider whether you want the agent to probe filesystem locations. If the publisher can confirm why the config path is needed (and that no unrelated credentials will be read or stored), the mismatch would be explainable; until then treat the skill as suspicious rather than benign.

Getting Started

Send me your audio files and I'll handle the speech to text transcription. Or just describe what you're after.

Try saying:

• "convert a 3-minute podcast recording into a 1080p MP4"
• "transcribe this audio and add the text as captions on screen"
• "converting spoken audio into on-screen text captions for podcasters, content creators, educators"

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.

Audio to Text — Convert Audio into Captioned Video

This tool takes your audio files and runs speech to text transcription through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute podcast recording and want to transcribe this audio and add the text as captions on screen — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: cleaner audio with less background noise produces more accurate transcriptions.

Matching Input to Actions

User prompts referencing audio to text, 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	❌

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.

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":"<lang>"}. 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/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

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

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

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

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

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.

Backend Response Translation

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

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute export workflow

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)

Common Workflows

Quick edit: Upload → "transcribe this audio and add the text as captions on screen" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "transcribe this audio and add the text as captions on screen" — concrete instructions get better results.

Max file size is 500MB. Stick to MP3, MP4, WAV, M4A for the smoothest experience.

Export as MP4 for widest compatibility across platforms and devices.