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 minimax-speechgit 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/minimax-speech)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/minimax-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/minimax-speech/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/minimax-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/minimax-speech.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 16 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 | $0.00105 | $0.05618 |
| Opus 5 | $0.00053 | $0.02809 |
| Sonnet 5 | $0.00021 | $0.01124 |
| Haiku 4.5 | $0.00011 | $0.00562 |
Grade A, and why
minimax-speech 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax speech production
Use MiniMax when the production goal is generated speech: narration, localized VO, ad reads, audiobook-style segments, synthetic dialogue, product walkthroughs, voice-agent responses, or approved voice cloning. Do not use this skill for MiniMax video, music generation, image generation, or general LLM calls except where they affect speech production.
The facts below were verified against official MiniMax API documentation, release notes, pricing, and policy pages on 2026-07-10. Treat model IDs, prices, rate limits, retention windows, voice lists, and policy language as volatile; re-check before a paid or regulated production run.
Capability boundary
Documented MiniMax speech capabilities:
- Synchronous text-to-audio over HTTP:
POST https://api.minimax.io/v1/t2a_v2. - Synchronous text-to-audio over WebSocket:
wss://api.minimax.io/ws/v1/t2a_v2. - Asynchronous long-form text-to-audio: create a task with
POST /v1/t2a_async_v2, query it, then retrieve the generated file. - System voices, cloned voices, and text-designed voices, queryable through Voice Management.
- Rapid voice cloning through file upload plus
POST /v1/voice_clone. - Voice design through
POST /v1/voice_design, where a text description produces a generatedvoice_idand preview audio. - Subtitle timestamp generation from TTS (
sentence,word, orword_streamingdepending on streaming mode). - An ASR-based validation check inside voice cloning when
text_validationis provided.
Not documented as standalone production APIs in the official docs index as of 2026-07-10:
- Standalone speech recognition / transcription.
- Speech-to-speech dubbing.
- Voice conversion from arbitrary source speech to a target voice while preserving timing.
- A separate low-latency conversational turn-taking API beyond T2A WebSocket streaming.
If a user asks for transcription, voice conversion, or full dubbing, combine MiniMax TTS with another documented ASR/alignment/dubbing provider, or explain that MiniMax’s official speech surface does not currently expose that workflow directly.
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 · 400 lines · 105 tokens per session scan A 402fd7ab2823
minimax-speech is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 5,618 once invoked, about $0.0005 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.