vobiz-audio-streams

vobiz-audio-streams is a skill for Claude Code from vobiz-ai/Agent-Skills. It costs 32 tokens per session (2,913 once invoked), scanned A, original, MIT.

A connection for sending live telephone-call audio to and from your server over WebSocket, a persistent connection for real-time data exchange.

In plain words
What is it for?
Use it for AI phone agents, live transcription, custom speech-to-text or text-to-speech pipelines, and other systems that need raw audio frames.
Why use it?
It lets voice applications process audio during a call instead of waiting for a recording after the call ends.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vobiz plugin — 13 skills, 1 MCP server shipped together

Good fit Use it for AI phone agents, live transcription, custom speech-to-text or text-to-speech pipelines, and other systems that need raw audio frames.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vobiz-ai/agent-skills/vobiz-audio-streams
Install

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.

Any agent
npx skills add vobiz-ai/Agent-Skills --skill vobiz-audio-streams
Clone the repo
git clone --depth 1 https://github.com/vobiz-ai/Agent-Skills

Made for: Claude Code.

Or install vobiz, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

Wrote 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.

agentmods badge for vobiz-audio-streams

README.md
[![agentmods](https://agentmods.dev/badge/skills/vobiz-ai/agent-skills/vobiz-audio-streams/github.svg)](https://agentmods.dev/skills/vobiz-ai/agent-skills/vobiz-audio-streams)
Your own site
<a href="https://agentmods.dev/skills/vobiz-ai/agent-skills/vobiz-audio-streams"><img src="https://agentmods.dev/badge/skills/vobiz-ai/agent-skills/vobiz-audio-streams/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.

agentmods 80×15 button for vobiz-audio-streams

Your own site · 80×15
<a href="https://agentmods.dev/skills/vobiz-ai/agent-skills/vobiz-audio-streams"><img src="https://agentmods.dev/badge/skills/vobiz-ai/agent-skills/vobiz-audio-streams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,913 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.02913
Opus 5 $0.00016 $0.01456
Sonnet 5 $0.00006 $0.00583
Haiku 4.5 $0.00003 $0.00291

Measured 12d ago against content hash f0f7f40e341c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vobiz-audio-streams 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 12d 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.

skills/vobiz-audio-streams/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vobiz Audio Streams skill

Use this for AI voice agents, real-time transcription, custom STT/TTS pipelines, or any workflow that needs raw audio frames rather than just recordings.

How it works

  1. During a call, your VobizXML answer handler returns a <Stream bidirectional="true">wss://your-server/ws</Stream> verb.
  2. Vobiz opens a WebSocket to your server and sends a single start event with callId, streamId, and mediaFormat.
  3. Audio frames flow Vobiz → your server as media events (~50 per second per track, 20 ms each).
  4. For bidirectional streams, your server sends playAudio events back, plus checkpoint, clearAudio, and stop control messages.
  5. When the call ends, the WebSocket closes - there is no inbound stop event.

Two ways to start a stream

Approach When to use
<Stream> XML verb The call is being set up by your answer handler. Best for AI agents that own the call from the first ring. Bidirectional playback requires this path.
REST POST .../Stream/ The call is already live and you want to attach (or fork) audio mid-call - e.g. start transcription after a transfer. Returns a stream_id you can later list/get/stop.

REST streams are forks: bidirectional=true over REST still requires audio_track=inbound. For full duplex voice agents, prefer the XML verb.

REST endpoints

Base: https://api.vobiz.ai/api/v1. Auth headers: X-Auth-ID, X-Auth-Token.

Op Method + Path Notes
Start stream POST /Account/{auth_id}/Call/{call_uuid}/Stream/ Body needs service_url; returns stream_id (202).
List streams GET /Account/{auth_id}/Call/{call_uuid}/Stream/ Active + stopped, paginated (limit/offset).
Get stream GET /Account/{auth_id}/Call/{call_uuid}/Stream/{stream_id}/ Full Stream object; 404 if unknown.
Stop one stream DELETE /Account/{auth_id}/Call/{call_uuid}/Stream/{stream_id}/ 204; leaves other forks running.
Stop all streams DELETE /Account/{auth_id}/Call/{call_uuid}/Stream/ 204; tears down every fork on the call.

Read the full file on GitHub · 198 lines

Changes

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.

  1. 12d ago First seen · 198 lines · 32 tokens per session scan A f0f7f40e341c

Subscribe to this mod's changes

vobiz-audio-streams is a skill published in the GitHub repository vobiz-ai/Agent-Skills (2 stars, last pushed 23d ago), licensed MIT. It adds 32 tokens to every session and 2,913 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

architecture-decision-record

ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.

yonatangross/orchestkit · 38 tokens

azure-event-grid-webhooks

Receive and validate Azure Event Grid webhook deliveries. Use when setting up an Event Grid WebHook event handler, implementing the Microsoft.EventGrid.SubscriptionValidationEvent handshake (echo data.validationCode as validationResponse with HTTP 200), implementing the CloudEvents v1.0 HTTP OPTIONS abuse-protection…

hookdeck/webhook-skills · 148 tokens

baselinker-webhooks

Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature…

hookdeck/webhook-skills · 131 tokens

cronofy-webhooks

Receive and verify Cronofy push notifications (webhooks). Use when setting up Cronofy notification channels, debugging Cronofy-HMAC-SHA256 verification, or handling Cronofy calendar events like verification, change, profiledisconnected, conferencingprofiledisconnected, profileinitialsynccompleted, and gdprrequested.…

hookdeck/webhook-skills · 102 tokens

clio-webhooks

Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the X-Hook-Secret handshake, or handling legal practice events like matter.created, contact.updated, activity.created, or bill events.

hookdeck/webhook-skills · 64 tokens

favro-webhooks

Receive and verify Favro webhooks. Use when setting up Favro webhook handlers, debugging X-Favro-Webhook signature verification, accepting the setup ping, or handling card events (card.created, card.committed, card.moved, card.updated, card.deleted) and comment events (comment.created, comment.updated…

hookdeck/webhook-skills · 121 tokens