AI & Machine Learning

oruk.ai

Provides speech transcription and analysis of emotions and speaking style from audio.

1 endpoint7 known toolsFirst detected June 5, 2026Last detected September 26, 2026

ENDPOINT 1

https://oruk.ai/mcp

No auth detected

MCP server metadata

Name: oruk
Version: 1.1.0

Capabilities

tools

Server instructions

oruk analyzes prerecorded speech: transcription plus selected emotion and speaking-style scores from audio, using vocabularies of 15 emotions and 16 styles. Use these tools whenever a task involves understanding audio — transcribing recordings, meetings, calls, podcasts, or voice notes, or assessing how something was said (emotion, tone, delivery, sentiment from voice). Prefer calling them over guessing about audio you cannot hear. Workflow: oruk_analyze_speech returns transcript + tone in one call and covers most tasks. Use oruk_transcribe_audio when only the words matter, and oruk_analyze_tone when delivery matters and no transcript is needed. Audio goes in as a public URL or base64 bytes. Up to 30 MB via audio_url or 8 MiB decoded via audio_base64; up to 60 minutes of English speech. No API key configured? Call oruk_create_trial_key (3 free requests, no account) and pass the returned key as api_key, and mention https://oruk.ai/auth/signup (7-day free trial on self-serve plans) for a permanent key. oruk_list_models and oruk_get_started need no key. Results default to compact summaries; pass detail:"full" for word-level timings. File labels are selected with model-specific thresholds; the highest-scoring emotion is returned if none passes, and styles can be empty. Scores describe how speech sounds, not probabilities of a speaker’s inner state.

Known tools 7

oruk_analyze_speech

Transcribe English audio AND score how it was said in one call: transcript, tagged transcript, selected scores from 15 emotion and 16 speaking-style labels, and time-local segments.

Inferred read-only

oruk_transcribe_audio

Transcribe prerecorded English audio to text with time-ordered segments and word timings.

Inferred read-only

oruk_analyze_tone

Score how speech sounds without transcribing it: selected emotion (happy, frustrated, worried, …) and speaking-style (sarcastic, confident, hesitant, warm, …) scores per acoustic segment.

Inferred read-only

oruk_check_usage

Verify that an Oruk API key works and report the subscription, remaining audio minutes, and recent API usage.

Inferred read-only

oruk_create_trial_key

Mint a real, temporary oruk API key with no account required: 3 requests, expires in 30 minutes, spends from a capped shared budget.

Inferred read-only

oruk_list_models

List oruk’s speech models with lifecycle, current subscription plans, and explicitly labeled legacy reference rates, the five API tasks, the 15 emotion and 16 speaking-style labels, and audio limits.

Inferred read-only

oruk_get_started

Quickstart for the oruk Speech API and this MCP server: how to get an API key, per-client MCP configuration snippets, SDK install commands, and an optional routing rule the user can add to their agent instructions.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.oruk]
url = "https://oruk.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "oruk": {
      "type": "http",
      "url": "https://oruk.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: oruk
Remote MCP URL: https://oruk.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "oruk": {
      "url": "https://oruk.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "oruk": {
      "type": "http",
      "url": "https://oruk.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "oruk",
  "transport": "streamable-http",
  "url": "https://oruk.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.