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 deepgram-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/deepgram-speech)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/deepgram-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/deepgram-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/deepgram-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/deepgram-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 227 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 336 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 | $0.00058 | $0.04960 |
| Opus 5 | $0.00029 | $0.02480 |
| Sonnet 5 | $0.00012 | $0.00992 |
| Haiku 4.5 | $0.00006 | $0.00496 |
Grade A, and why
deepgram-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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepgram speech production
Use this skill when Deepgram is a candidate provider for transcription, captioning, speech analytics, voice-agent audio, or text-to-speech assets. Treat Deepgram as a production speech platform, not as a generic "make audio" button: choose the endpoint, model, features, and custody plan from the deliverable's latency, accuracy, language, privacy, and artifact requirements.
Facts in this skill were checked against official Deepgram documentation and pricing on 2026-07-10. Verify volatile items again before spend or launch: public model IDs, language support, add-on prices, concurrency, regional availability, and early-access controls.
Primary official evidence used:
- API overview: https://developers.deepgram.com/reference/deepgram-api-overview
- STT getting started: https://developers.deepgram.com/docs/stt/getting-started
- Pre-recorded STT API: https://developers.deepgram.com/reference/speech-to-text/listen-pre-recorded
- Streaming STT API: https://developers.deepgram.com/reference/speech-to-text/listen-streaming
- Models and languages: https://developers.deepgram.com/docs/models-languages-overview
- Flux docs: https://developers.deepgram.com/docs/flux/agent and https://developers.deepgram.com/reference/speech-to-text/listen-flux
- Diarization: https://developers.deepgram.com/docs/diarization
- Captions guide: https://developers.deepgram.com/docs/automatically-generating-webvtt-and-srt-captions
- Audio Intelligence overview: https://developers.deepgram.com/docs/audio-intelligence
- STT Intelligence feature matrix: https://developers.deepgram.com/docs/stt-intelligence-feature-overview
- Aura TTS models: https://developers.deepgram.com/docs/tts-models
- TTS REST and streaming: https://developers.deepgram.com/docs/text-to-speech and https://developers.deepgram.com/docs/streaming-text-to-speech
- TTS latency and controls: https://developers.deepgram.com/docs/text-to-speech-latency and https://developers.deepgram.com/docs/tts-voice-controls
- Voice Agent configuration/API: https://developers.deepgram.com/docs/configure-voice-agent and https://developers.deepgram.com/reference/voice-agent/voice-agent
- Rate limits: https://developers.deepgram.com/reference/api-rate-limits
- Pricing: https://deepgram.com/pricing
- Security/privacy/compliance: https://deepgram.com/data-security, https://developers.deepgram.com/trust-security/data-privacy-compliance, https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program
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 · 359 lines · 58 tokens per session scan A d79215f202fb
deepgram-speech is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 4,960 once invoked, about $0.0003 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…