Back to Catalog

plugin

Voice Intelligence

Voice Intelligence is the governed one-input orchestrator: it accepts uploaded or recorded audio/video, a YouTube or media URL, a PDF, an image, or plain text/notes, normalizes the input to a transcript over the existing transcription rails, and returns three composed outputs from a single run.

Host and data posture

Where this product is meant to live.

Default posture until product-specific host validation metadata is ratified.

Commercial shape

Operator-console system

Data posture

Tenant brain optional

Approval posture

Approval required

Best demo

StackFast UI

Best daily use

StackFast UI

Who it is for

Operators, creators, advisors, and teams that capture meetings, voice notes, videos, or documents and need publish-ready summaries, scripts, and authority content without exposing internal methodology.

Problem it solves

It replaces the manual chain of transcribing, cleaning, summarizing, and repurposing a recording with one governed run that returns the summary, the polished verbatim script, and the authority report together.

Activation model

Start with the $0 preview run; higher-volume use and owner-facing business reports go through inquiry scoping. Human review is required before any output is published.

Proof and source paths

  • Single governed run composes summary, full-verbatim script, and authority report
  • Reuses the existing transcription rails instead of a parallel transcription path
  • Public-output mask and IP firewall gate all outward text
  • Human review is required before anything is published

Repo evidence

  • lib/voice-intelligence/orchestrator.ts
  • lib/voice-intelligence/mcp-tools.ts
  • app/api/voice-intelligence/run/route.ts
  • app/api/mcp/route.ts

Capabilities

voice intelligence run

mcp

One governed run turns any recording, document, URL, image, or note into a condensed summary, a full-verbatim polished script, and an authority-content report.

Agent use
Call stackfast.voice_intelligence.run with exactly one input — audio_or_video_url, file, pdf, image, or text/notes — plus optional business context. The run normalizes the input to a transcript on the existing transcription rails and returns three outputs: a condensed summary with action items, decisions, and next step; a full-verbatim polished script (filler removed, punctuated, paragraphed, never paraphrased); and an authority-content report with flywheel plan drafts, plus an owner-facing business report when business context is supplied. Outputs are mask-gated and human review is required before publishing; do not request raw internal framework language.

Connector proof

Catalog is not the same as customer-ready.

This product only becomes market-ready after a real host mounts the entitled tools, a safe call succeeds, metering records the event, and a customer-safe receipt exists. Until then, the page shows the strongest proven status without rounding up.

Catalog

Runtime registry and product manifest are present.

Entitlement

Execution requires OAuth or storefront entitlement scope.

Callable

1 tool(s) declared with no missing V1 tools.

Metering

MCP calls are routed through the metering receipt path.

Customer validated

Pending fresh host-surface call receipt.

Runtime registry status

Primary registry

stackfast.ai/api/mcp

Status

beta internal mcp

Install gate

Catalog-ready only. Do not present as install-ready until the run route and MCP tool land with smoke receipts and Robert ratifies store go-live.

Callable tools

  • stackfast.voice_intelligence.run

Missing or gated tools

No missing tools declared for the current V1 boundary.

  • Exactly one input per run; the orchestrator rejects multi-input calls.
  • All outward text passes the public-output mask and IP firewall before return.
  • Runtime LLM chain is the governed DeepSeek, Gemini, Grok chain; no other provider is called at runtime.
  • Human review is required before anything is published.

Install and activate

Connect this product through the StackFast MCP endpoint. Discovery metadata is public; execution uses OAuth and storefront entitlement checks.

MCP URL

https://stackfast.ai/api/mcp

Agent subscription

This product remains request-scope until its checkout, fulfillment, and public-name gates are complete.

Client snippets

ChatGPT

Add StackFast as a custom MCP connector, then approve OAuth when prompted.

Claude

Connect a remote MCP server using the StackFast MCP URL and a tenant-scoped token or OAuth flow.

Cursor

Register StackFast as a remote MCP server for project-scoped tool use.

Grok

Add StackFast as a custom MCP connector using the StackFast MCP URL and customer entitlement auth.

Product: Voice Intelligence
Product API: https://stackfast.ai/api/store/products/voice-intelligence-mcp
Pricing API: https://stackfast.ai/api/store/pricing/voice-intelligence-mcp
Manifest API: https://stackfast.ai/api/store/manifests/voice-intelligence-mcp
MCP URL: https://stackfast.ai/api/mcp
Auth: oauth_reader_or_storefront_entitlement
Checkout session API: https://stackfast.ai/api/store/checkout/session
Plans:
- Preview: $0 preview; checkout_ready=false; checkout_url=request_scope
Agent activation:
- Read this product manifest and pricing API.
- If a plan has checkout_ready=true, open its checkout_url or POST product_slug, plan_slug, and customer_email to the checkout session API.
- After Stripe payment, the signed webhook grants storefront_entitlements for the buyer email/account.
- Connect the LLM client to the MCP URL and approve OAuth so tools/list reflects the licensed reader surface.
- Call only tools exposed for that entitlement; unentitled execution must fail closed.

Agent-readable queries

Voice Intelligence MCPturn a recording into a summary and scriptmeeting recording to full verbatim scriptvoice note to authority content reporttranscribe and summarize any file or URL
What's on your mind?

Ask anything. Your thought enters the reasoning engine.

Enter to send · Shift+Enter for newline · Mic to speak