voice-ai skillA
voice-ai is agent-read markdown (skill) from coco-research/coco: Voice AI architecture and implementation guide. Covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency) and pipeline (STT->LLM->TTS, more control). Includes provider-specific patterns for OpenAI Realtime, Vapi, Deepgram, ElevenLabs, and LiveKit. Use when building voice agents, voice-enabled apps, or real-time conversational AI..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Voice AI — Architecture & Implementation You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency — every component adds milliseconds, and the sum determines whether conversations feel natural or awkward. ## Core Insight: Two Architectures | Architecture | Latency | Control | Best For | |-------------|---------|---------|----------| | Speech-to-Speech (S2S) | Lowest (~200-400ms) | Less controllable | Natural conversation, emotion preservation | | Pipeline (STT->LLM->TTS) | Higher (~600-1200ms) | Full control at each step | Custom logic, debugging, provider mixing | --- ## Part 1: Architecture Patterns ### Speech-to-Speech Architecture Direct audio-to-audio processing for lowest latency. Models like OpenAI Realtime API preserve emotion and achieve the most natural conversation flow. **Strengths:** - Preserves vocal emotion and nuance - Lowest end-to-end latency - Single provider simplicity **Weaknesses:** - Less controllable intermediate steps - Harder to debug - Provider lock-in ### Pipeline Architecture Separate STT -> LLM -> TTS for maximum control at each step. **Strengths:** …
Read the whole file at its exact version.
How to install
mdr add coco-research/coco/voice-ai@git:20260802.1479e32mdr add coco-research/coco/voice-ai@sha256:6766c77b062aedb7Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_fbs4vgrcyxu4y2nu)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260802.1479e32 latest | 2026-08-02 | 1479e32 | 11,432 B | A | view · diff |
| git:20260426.d53cc6c | 2026-04-26 | d53cc6c | 11,412 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11432 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
coco-research/coco · 478 stars · license NOASSERTION · pushed 2026-09-25 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fbs4vgrcyxu4y2nu GET https://markdownregistry.com/api/v1/resolve?ref=coco-research/coco/voice-ai GET https://markdownregistry.com/api/v1/blob/6766c77b062aedb74c5d7c114372a40b30180a45c8df4d33c4448008aec84ae0
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.