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 google-cloud-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/google-cloud-speech)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-cloud-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-cloud-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/google-cloud-speech"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-cloud-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.05311 |
| Opus 5 | $0.00042 | $0.02655 |
| Sonnet 5 | $0.00017 | $0.01062 |
| Haiku 4.5 | $0.00008 | $0.00531 |
Grade A, and why
google-cloud-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 8d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Cloud Speech for media production
Use Google Cloud Speech as a provider option when the job is fundamentally about speech audio:
- Transcribe existing audio/video into scripts, searchable text, edits, subtitles, captions, or speaker notes.
- Generate SRT/WebVTT captions from long media.
- Plan live captions or real-time transcript features.
- Create synthetic narration, dialogue prototypes, educational voiceovers, IVR-style prompts, or localized voice tracks.
- Use Google voice families such as Chirp 3 HD, Gemini-TTS, Studio, Neural2, WaveNet, or Standard when the production brief values Google Cloud governance, scale, regional controls, or existing GCP infrastructure.
- Create a consented custom voice only when official access, voice-owner consent, and rights review are present.
Do not use this skill as a generic audio-editing, music, denoise, DAW, mixing, or video-localization skill. Google Cloud Speech can produce transcripts and voice assets, but production finishing still needs editing, loudness normalization, sync, QC, and often translation tools outside the Speech APIs.
Volatile facts below were verified against official Google Cloud documentation on 2026-07-10. Re-check model IDs, launch stages, regional endpoints, quotas, and prices before committing spend or compliance claims.
API boundary
Google exposes related but separate services:
- Cloud Speech-to-Text (STT): recognition/transcription from audio to text. For new media workflows, prefer API V2 unless an existing integration requires V1. V2 adds recognizer resources, regionalized service patterns, customer-managed encryption key support for resources and batch transcription, and audio auto-detect.
- Cloud Text-to-Speech (TTS): speech synthesis from plain text, SSML, markup, or model-specific prompted text into playable audio.
- Gemini-TTS appears in current Cloud Text-to-Speech documentation as a newer TTS family with text-prompted style control; some routes may involve Vertex AI permissions or endpoints. Verify the exact API route in the current docs before implementation.
- Instant Custom Voice is a Cloud TTS feature for creating a voice cloning key from consent and reference audio, but access is restricted to allow-listed users.
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.
- 8d ago First seen · 374 lines · 84 tokens per session scan A 40933e830a65
google-cloud-speech is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 5,311 once invoked, about $0.0004 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
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…
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.
Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.