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 gemini-live-audiogit 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/gemini-live-audio)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/gemini-live-audio"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/gemini-live-audio/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/gemini-live-audio"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/gemini-live-audio.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 Excessive Agency · line 144 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 | $0.00095 | $0.05672 |
| Opus 5 | $0.00048 | $0.02836 |
| Sonnet 5 | $0.00019 | $0.01134 |
| Haiku 4.5 | $0.00010 | $0.00567 |
Grade A, and why
gemini-live-audio 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Live audio
Use this skill when the job is a live spoken interaction, not a batch narration render. Gemini Live is for bidirectional sessions: microphone or streamed media in, spoken model output back, with turn-taking, interruptions, tools, and session lifecycle concerns. If the deliverable is a finished voiceover, audiobook, podcast narration, or offline transcript, prefer a TTS or speech-to-text skill unless the user explicitly needs live turn-taking.
All volatile facts below were verified against official Google AI and Google Cloud documentation on 2026-07-10. Model names, preview/GA status, pricing, rate limits, supported regions, and governance controls change often; re-check official docs before production launch, procurement commitments, or regulated deployment.
Documented facts
Current shape of the product
- Gemini Live API is a stateful WebSocket API for low-latency voice and vision interactions. It can process continuous streams of audio, images, text, and, in API references, video; it returns spoken/audio output and can also return text/function-call events depending on configuration and model.
- Google AI Live API pages currently note that the Interactions API is generally available and recommended for access to the latest features and models. Treat this skill as Live-API-specific guidance; for a greenfield production agent, verify whether Live API or Interactions API is the intended Google surface before committing architecture.
- Google AI Developer API docs mark Live API as Preview. Google Cloud / Gemini Enterprise Agent Platform docs separately document Vertex/enterprise availability and a GA Gemini 2.5 Flash Native Audio model. Treat Developer API and Gemini Enterprise Agent Platform as distinct deployment surfaces with different auth, terms, locations, governance, quotas, and support.
- The principal Live agent model family documented on 2026-07-10 includes
gemini-3.1-flash-live-previewin the Developer API docs andgemini-live-2.5-flash-native-audio/ Gemini 2.5 Flash Live API Native Audio in Gemini Enterprise Agent Platform docs. Live Translation is documented separately withgemini-3.5-live-translate-preview. - Use Live Agent mode when the model is an assistant that reasons, asks questions, calls tools, and handles turns. Use Live Translation mode when the model is an interpreter pipeline: audio in one language, translated audio out another. Live Translation is documented as audio-restricted, translation-only, and not a tool/instruction-driven agent surface.
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 · 386 lines · 95 tokens per session scan A 81e83d0eb38f
gemini-live-audio is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 5,672 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-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.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…