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 resemble-chatterboxgit 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/resemble-chatterbox)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/resemble-chatterbox"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/resemble-chatterbox/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/resemble-chatterbox"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/resemble-chatterbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 158 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.
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 | $0.00110 | $0.03675 |
| Opus 5 | $0.00055 | $0.01837 |
| Sonnet 5 | $0.00022 | $0.00735 |
| Haiku 4.5 | $0.00011 | $0.00367 |
Grade A, and why
resemble-chatterbox scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://f.cluster.resemble.ai/synthesize" \ How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resemble Chatterbox
Use Chatterbox when the production needs expressive AI speech, zero-shot/reference-voice behavior, local or on-prem deployment, or Resemble-hosted TTS with Chatterbox-family voices. Do not use it as a generic "celebrity impersonation" tool. Treat every reference voice as biometric/personal data and require documented rights before generation.
Volatile facts in this skill were verified on 2026-07-10 from official Resemble AI, GitHub, Hugging Face, and Resemble documentation sources listed at the end.
Choose the route first
Documented facts:
- Local/open route: Resemble publishes Chatterbox-family code and weights through the official
resemble-ai/chatterboxGitHub repository andResembleAI/chatterboxHugging Face model card under MIT license. The local package installs withpip install chatterbox-ttsand exposes Python classes such asChatterboxTTSandChatterboxMultilingualTTS. - Hosted route: Resemble's synthesis API uses
https://f.cluster.resemble.ai/synthesizefor synchronous TTS and a streaming HTTP endpoint for chunked WAV. Requests authenticate withAuthorization: Bearer YOUR_API_KEY. - Hosted Chatterbox model versions documented by Resemble include Chatterbox, Chatterbox-Turbo, and Chatterbox Multilingual. Hosted Turbo is selected with the
modelvaluechatterbox-turbo; Resemble's model-version page also lists version codestts-v4andtts-v4-turbo.
Production decision:
- Prefer local/open Chatterbox when the project requires on-prem control, no vendor audio upload, custom batching, offline evaluation, or permissive model modification.
- Prefer hosted Resemble when the project needs managed voices, streaming API delivery, low ops burden, team voice libraries, billing support, or production scale without managing GPU inference.
- Prefer Turbo for low-latency agents or dialog loops where its documented paralinguistic tag support matters.
- Prefer Multilingual V3 for cross-language voice cloning or localization; use Single Language Pack models when a priority language or regional dialect needs tighter pronunciation quality.
- Prefer original English Chatterbox when the job is English narration/character voice with emotion exaggeration and local creative control, and multilingual coverage is not required.
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 · 222 lines · 110 tokens per session scan A 270fc4ffc900
resemble-chatterbox is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 3,675 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.