Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Voice Ai Engine Development

skill · Dokhacgiakhoa/antigravity-ideNOASSERTION licenceAudited 19 Oct 2026 · source d1a0c85a714a

★ 508pushed 130 days agoversion 4.1.0-fractal
✓SAFEGrade B · 89/100 · 19 Oct 2026 · d1a0c85
508repo stars · whole Dokhacgiakhoa/antigravity-ide

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit d1a0c85a714a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Architecting real-time Voice AI agents.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Voice Ai Engine Development (Dokhacgiakhoa/antigravity-ide)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/dokhacgiakhoa/voice-ai-engine-development

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha d1a0c85a714a · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherDokhacgiakhoa GitHub userOwner of the repository this skill is read from
  • Source folderDokhacgiakhoa/antigravity-ide/.agent/skills/voice-ai-engine-developmentThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdictd1a0c85a714aA new audit runs when the source changes
  • Repository statusNot archivedLast push 130 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Architecting real-time Voice AI agents.

---
name: voice-ai-engine-development
description: Architecting real-time Voice AI agents.
category: development
version: 4.1.0-fractal
layer: master-skill
---

# Voice AI Engine Development

> **Goal**: Build low-latency, conversational Voice AI agents capable of full-duplex communication.

## 1. The Voice Pipeline (Latency is King)

The total loop Latency (Voice-to-Ear) should be < 1000ms (Ideal < 500ms).

1.  **Transport**: WebRTC (preferred for browser) or WebSocket (server-server).
2.  **VAD (Voice Activity Detection)**: Detect when user starts/stops speaking.
    - *Tools*: Silero VAD, WebRTC VAD.
3.  **STT (Speech-to-Text)**: Transcribe audio to text.
    - *Tools*: Deepgram (fastest), Whisper (high accuracy but slower), AssemblyAI.
4.  **LLM (Brain)**: Process text and generate response.
    - *Tools*: Groq (Llama 3), GPT-4o, Claude 3.5 Sonnet.
5.  **TTS (Text-to-Speech)**: Convert response to audio.
    - *Tools*: ElevenLabs (Quality), Cartesia (Speed), OpenAI TTS.

## 2. Architecture Patterns

- **Streaming Pipeline**: DO NOT wait for full transcription or full generation. Stream everything.
    - User Audio Stream -> VAD -> STT Stream -> LLM Stream -> TTS Stream -> Audio Output.
- **Interruption Handling (Barge-in)**:
    - If VAD detects user speech while AI is talking -> Immediately CUT text generation and audio playback. Clear buffers.

## 3. Implementation Stack

- **Backend**: Python (FastAPI) or Node.js. Python ecosystem is stronger for audio processing (numpy/scipy).
- **Frameworks**:
    - **Pipecat**: Open source framework for building voice agents.
    - **LiveKit**: WebRTC infrastructure for real-time audio/video.
    - **Twilio**: For telephony integration.

## 4. Optimization Techniques

- **Optimistic VAD**: Tune VAD to be sensitive to start, but careful with "silence" timeout (usually 500ms-800ms) to detect end of turn.
- **Prompt Engineering**: Instruct LLM to be concise and conversational.
    - *System Prompt*: "You are a helpful voice assistant. Keep responses short (1-2 sentences). Do not use markdown or emojis."
- **Audio Formats**: Use OPUS or PCM (16khz/24khz/48khz) for transmission. Avoid MP3 transcoding latency.

## 5. Debugging & Metrics

- **WER (Word Error Rate)**: For STT accuracy.
- **TTFT (Time to First Token)**: LLM speed.
- **TTA (Time to Audio)**: The critical metric. Time from user silence to first AI sound.

---

**Common Pitfalls**:
- Echo cancellation issues (User hears themselves). Use WebRTC's built-in AEC.
- Hallucination in STT (Whisper transcribing silence).
- Race conditions during interruptions.

Excerpt, first 2,596 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit d1a0c85

Download folder ↗
git clone https://github.com/Dokhacgiakhoa/antigravity-ide
git -C antigravity-ide checkout d1a0c85a714a

The author documents no install command, so this uses the repository directly. Our verdict covers commit d1a0c85a714a only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source d1a0c85a714a

Questions about Voice Ai Engine Development

Is Voice Ai Engine Development safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Voice Ai Engine Development access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (d1a0c85a714a), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.