Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add calesthio/generative-media-skills --skill sync-labs-lipsyncgit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/calesthio/generative-media-skills/sync-labs-lipsync)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/sync-labs-lipsync"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/sync-labs-lipsync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/sync-labs-lipsync"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/sync-labs-lipsync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 76 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 84 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 403 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Output Handling · line 279 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
- medium Excessive Agency · line 375 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00156 | $0.06332 |
| Opus 5 | $0.00078 | $0.03166 |
| Sonnet 5 | $0.00031 | $0.01266 |
| Haiku 4.5 | $0.00016 | $0.00633 |
Grade A, and why
sync-labs-lipsync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Labs lip sync and visual dubbing
Sync Labs (product domain sync.so, API host api.sync.so) is a hosted API and web
studio that regenerates a speaker's mouth (and, on newer models, jaw/expression/head)
to match a new audio track. It does not generate whole people or scenes: the input is
an existing talking-head video (or, on sync-3, a single still face), plus target
audio (a file, a hosted URL, or text synthesized through an integrated TTS provider).
Everything outside the driven face region — background, body, hair, clothing — is left
untouched and composited around the regenerated face. (Documented: sync.so/docs
introduction and "how AI lip sync works", verified 2026-07-10.)
Use this skill when the job is: dubbing/localizing a video into another language, re-timing lips to corrected or re-recorded audio (ADR-style), personalizing a base video with per-recipient names, cutting podcast/interview clips with clean lips, or animating a portrait photo from a voiceover. Do not reach for it to generate a face from scratch, to swap identities, or to produce a full avatar from text alone — those are different product categories.
What the models are and how to choose
All model facts below are from sync.so/docs (models pages and pricing), verified 2026-07-10. Prices are quoted per second of output at 25 fps and move with plan tier, so treat them as dated reference, not a contract.
| Model ID | Face resolution | Obstruction handling | Speed (docs) | Price/sec @25fps | Built for |
|---|---|---|---|---|---|
lipsync-1.9.0-beta |
face crop | none | ~3x real-time (fastest) | $0.02–0.025 | cheap, simple, frontal clips; generic mouth motion |
lipsync-2 |
512×512 crop | optional (occlusion_detection_enabled) |
~1x real-time | $0.04–0.05 | general-purpose default; preserves each speaker's style |
lipsync-2-pro |
512×512 + diffusion super-res | optional | ~0.5–0.7x (1.5–2x slower than lipsync-2) | $0.067–0.083 | premium detail on beards, teeth, fine facial features |
sync-3 |
4K native, full-shot | automatic, built-in | fast (processes whole shot at once) | $0.107–0.133 | close-ups, profiles/extreme angles, partial faces, still-image input |
react-1 |
expression/head editing | — | short clips only | (see pricing page) | change emotion, expression, and head motion, not just lips |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 416 lines · 156 tokens per session scan A a1a947c9cb74
sync-labs-lipsync is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 156 tokens to every session and 6,332 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-caption-layout-director
Lays out subtitles for an existing ClipTalk timeline, including top/bottom placement, safe margins, readable wrapping, bilingual order, and review rendering.
video-translate
Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5) Working with HeyGen's /v2/videotranslate…
translation
A translation tool for converting current text, conversations, or explicitly provided files into a target language while preserving their meaning and key information.
Stable Diffusion
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.