Text To Voice Generator

convert written text into voiced video files with this text-to-voice-generator skill. Works with TXT, DOCX, PDF, SRT files up to 200MB. content creators, mar...

Security Scan

The skill is mostly coherent for a cloud-based text→voice/export workflow, but there are inconsistencies and privacy-surface issues (unknown source, mismatched metadata, and instructions that read local paths and upload files) that you should understand before installing.

Purpose & Capability

The name/description (convert text to voiced video) matches the SKILL.md's API calls (session creation, uploads, render/export). Requiring a NEMO_TOKEN is proportionate for a third-party rendering API. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that is not listed in the registry metadata; this mismatch is unexplained and worth questioning the publisher about.

Instruction Scope

Runtime instructions include creating sessions, uploading files (multipart uploads referencing local paths), polling renders, and calling SSE endpoints — all expected. But the skill also instructs the agent to detect an install path (~/.clawhub/, ~/.cursor/skills/) and read YAML frontmatter at runtime to set attribution headers. Those filesystem checks and attribution enforcement expand what the agent will look at on the host and are not strictly necessary for core functionality.

Install Mechanism

There is no install spec and no code files — the skill is instruction-only. That reduces risk because nothing new is written to disk by the skill package itself.

Credentials

The only declared credential is NEMO_TOKEN, which is appropriate for calling the nemovideo API. However, the SKILL.md includes logic to issue an anonymous token if no NEMO_TOKEN is present and to read local config/install paths; those behaviors increase the surface area (the agent may access files and then transmit their contents). Also the discrepancy between registry metadata (no config paths) and the skill frontmatter (declares ~/.config/nemovideo/) is inconsistent and should be clarified.

Persistence & Privilege

The skill is not marked always:true and has no install scripts, so it does not request elevated or persistent platform privileges beyond normal runtime ability to call external APIs and access files the agent is allowed to read.

What to consider before installing

This skill appears to implement a normal cloud text→voice render workflow, but note: (1) the package source is unknown and the registry metadata/frontmatter disagree about config paths — ask the publisher to explain the discrepancy; (2) the skill will call an external API (mega-api-prod.nemovideo.ai) and will upload files you provide — do not submit sensitive secrets or private files unless you trust the service and its privacy policy; (3) it may check local install/config paths (~/.config/nemovideo/, ~/.clawhub/, ~/.cursor/skills/) and read YAML frontmatter to set headers — if you prefer, restrict the agent from accessing those paths or require explicit confirmation before any upload; (4) if you create a NEMO_TOKEN for use with this skill, prefer a limited-scope token or use the anonymous token path for testing. If you need higher assurance, request a trusted homepage, documentation, or publisher identity before installing.

Getting Started

Share your written text and I'll get started on AI voice generation. Or just tell me what you're thinking.

Try saying:

• "convert a 200-word product description script into a 1080p MP4"
• "convert this script to a natural-sounding female voice in American English"
• "converting written scripts into voiceover videos for content creators, marketers, 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.

Text to Voice Generator — Convert Text into Voiceover Videos

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

Here's a typical use: you send a a 200-word product description script, ask for convert this script to a natural-sounding female voice in American English, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter text blocks under 150 words produce the most natural-sounding output.

Matching Input to Actions

User prompts referencing text to voice generator, 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.

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

• X-Skill-Source: text-to-voice-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

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.

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)

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

Common Workflows

Quick edit: Upload → "convert this script to a natural-sounding female voice in American English" → Download MP4. Takes 20-40 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 "convert this script to a natural-sounding female voice in American English" — 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 platforms and devices.