Vellum Assistant is a personal AI assistant that remembers information about users, learns their preferences, and takes actions across connected apps. It is intended for people who want an assistant that can manage conversations, unfinished work, and proactive notifications over time. The catalogue skills, hooks, instruction, and setting configure or extend how the assistant works.
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 vellum-ai/vellum-assistant --skill deepgram-voicegit clone --depth 1 https://github.com/vellum-ai/vellum-assistantWrote 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/vellum-ai/vellum-assistant/deepgram-voice)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/deepgram-voice"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/deepgram-voice/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/vellum-ai/vellum-assistant/deepgram-voice"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/deepgram-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
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 →
- high Supply Chain · line 115 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 125 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Data Exfiltration · line 115 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 125 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 143 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 143 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 | $0.00030 | $0.02552 |
| Opus 5 | $0.00015 | $0.01276 |
| Sonnet 5 | $0.00006 | $0.00510 |
| Haiku 4.5 | $0.00003 | $0.00255 |
Grade C, and why
deepgram-voice scanned grade C with 2 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 11d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
To collect the API key securely: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.deepgram.com/v1/models" \ How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Deepgram provides text-to-speech voices (the Aura model family) for both in-app TTS and phone calls. Change the voice with the voice_config_update tool — it writes the voice to whichever TTS provider is currently active and pushes to the macOS app via SSE in one call:
voice_config_update setting="tts_voice_id" value="<aura-model-id>"
The voice lives under the active provider, not always Deepgram. The config key depends on
services.tts.provider:deepgram→services.tts.providers.deepgram.model,vellum(managed) →services.tts.providers.vellum.model,elevenlabs→services.tts.providers.elevenlabs.voiceId. Thevoice_config_updatetool (and theassistant tts voice <id>CLI command) handle this routing for you. Do NOTassistant config set services.tts.providers.deepgram.model ...blindly — on a managed (vellum) assistant that field is ignored, so the write "succeeds" but the voice never changes. See Setting the voice for the CLI fallback.The tables below apply when the active provider is
deepgram(BYO key) or managedvellum. Managed assistants synthesize Deepgram voices through the platform — the platform bills per rate-carded model and rejects voices it does not offer (the write succeeds but the voice fails on the next turn), so stick to current Aura-2 voices there. With a BYO key (setup below), any Aura model id from the catalog works. Other BYO TTS providers (elevenlabs,xai,fish-audio, …) use their own voice identifiers — never write a Deepgram Aura model id to them; see Getting to a Deepgram voice from another provider.
Getting to a Deepgram voice from another provider
Check the active provider first: assistant config get services.tts.provider.
- Already on managed
vellum? No provider change needed. The managed platform supports both Deepgram and ElevenLabs voices —services.tts.providers.vellum.modelaccepts either an Aura model id or an ElevenLabs voice id, so switching between a Deepgram and an ElevenLabs voice is just anothervoice_config_updatecall. - On a BYO provider (e.g.
elevenlabs) and the user wants a Deepgram voice? Two options — ask which they prefer. Switch with thevoice_config_updatetool, not rawassistant config set— the tool validates the switch (e.g. rejectsvellumwhen no platform connection exists, which a raw config write would leave silently broken):- Switch to managed
vellum(voice_config_update setting="tts_provider" value="vellum") — no Deepgram key needed; requires a platform connection and bills managed credits. Bonus: they keep access to both the Deepgram and ElevenLabs catalogs. - Switch to BYO
deepgram(voice_config_update setting="tts_provider" value="deepgram") — requires a Deepgram API key (setup below); usage bills their Deepgram account directly.
- Switch to managed
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.
- 11d ago First seen · 170 lines · 30 tokens per session scan C 10c4ea5ba931
deepgram-voice is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,225 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,552 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
make-viral-video
Build a short news-explainer video tuned for shareability. One striking moment per video; real fetched assets; self-heal validation; pluggable TTS (Gemini-free default, OpenAI fallback).
gemini-tts
Render text to mp3 via Google Gemini Flash TTS. Free-tier eligible (1500 req/day). Use for video narration, demo voiceovers, audio notes. Parallels openai-tts; default for make-viral-video.
image-generation
Generate and edit images using Gemini Flash Image, and generate videos using Veo. Supports text-to-image, image editing, text-to-video, and image-to-video.
audio-transcribe
Transcribes audio files and voice notes to text via Gemini 2.5-flash. Integrates with Slack, Discord, and Telegram bridges so voice clips surface as readable text in tasks.
screen-record
Start or stop a screen recording of the Mac via ffmpeg. Use when the user asks to record/capture their screen to a video file (a demo, a repro, a walkthrough) — not for a single still screenshot (use macos-tools screen capture for that).
openai-tts
Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes.