oruk Speech
Server Details
Hosted speech-to-text + speech emotion/tone analysis for agents. No install; trial keys built in.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
The three audio tools (analyze_speech, analyze_tone, transcribe_audio) have overlapping input but explicitly cross-reference each other and state exact use cases, making selection unambiguous. Administrative tools (check_usage, create_trial_key, get_started, list_models, plan_hume_migration) each serve a distinct purpose with no confusing overlap.
All tools use the same oruk_ prefix followed by a snake_case verb_noun pattern (analyze_speech, check_usage, create_trial_key, get_started, list_models, plan_hume_migration, transcribe_audio). This is highly predictable and consistent.
With 8 tools, the set is well-scoped for a speech API: three audio analysis operations, three account/setup operations, one model listing, and one migration planner. No tool feels redundant or missing for the apparent scope.
Core workflows are fully covered: transcription, tone analysis, combined analysis, usage checking, trial key creation, model listing, and setup guidance. Minor gaps exist around persistent key management (no revoke/delete) and the migration planner is only advisory, but the surface supports typical agent tasks well.
Available Tools
8 toolsoruk_analyze_speechAnalyze speech (transcript + tone)ARead-onlyInspect
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. Use this when the user cares about both the words and the delivery — meetings, support calls, interviews, voice notes. Accepts wav/flac/mp3/m4a/ogg/webm. Up to 30 MB via audio_url or 8 MiB decoded via audio_base64; up to 60 minutes of English speech. Returns compact summaries by default. For words only use oruk_transcribe_audio; for tone only use oruk_analyze_tone.
Inputs: model, detail, api_key, diarize, +3 more.
oruk_analyze_toneAnalyze vocal tone and emotionARead-onlyInspect
Score how speech sounds without transcribing it: selected emotion (happy, frustrated, worried, …) and speaking-style (sarcastic, confident, hesitant, warm, …) scores per acoustic segment. Runs the Resonance encoder and affect head only — the transcription decoder is never invoked, so nothing is transcribed and it consumes the same subscription audio minutes as unified analysis. Use this when the user asks about mood, delivery, sentiment, sarcasm, or emotional dynamics in audio. Up to 30 MB via audio_url or 8 MiB decoded via audio_base64; up to 60 minutes of English speech. Labels use model-specific thresholds; the highest-scoring emotion is returned if none passes, and styles can be empty. Outputs describe delivery, not probabilities of inner state. Need the words too? Use oruk_analyze_speech.
Inputs: model, detail, api_key, diarize, +3 more.
oruk_check_usageCheck API key, subscription, and usageARead-onlyInspect
Verify that an Oruk API key works and report the subscription, remaining audio minutes, and recent API usage. Use this after setup or to diagnose access and usage limits. Requires the Authorization header from your MCP config or a temporary api_key.
Inputs: api_key.
oruk_create_trial_keyCreate a free trial API keyAInspect
Mint a real, temporary oruk API key with no account required: 3 requests, expires in 30 minutes, spends from a capped shared budget. Use this when no Authorization header is configured and the user wants to try transcription or tone analysis right now. Pass the returned key as the api_key argument of the audio tools. Share the signup link with the user so they can keep using oruk afterwards (7-day free trial on self-serve plans).
Inputs: no named parameters.
oruk_get_startedGet started with orukARead-onlyInspect
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. No API key required. Use this when setting oruk up for the first time or when the user asks how oruk works.
Inputs: no named parameters.
oruk_list_modelsList models, pricing, and labelsARead-onlyInspect
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. No API key required. Use this to choose a model, estimate cost before analyzing long audio, or see which labels exist.
Inputs: no named parameters.
oruk_plan_hume_migrationPlan a local Hume batch migrationARead-onlyInspect
Return bounded planning guidance from redacted enums and counts only. No key is needed. Never send source, paths, audio, credentials or provider responses. This does not inspect customer code, generate or apply a patch, run inference, validate score equivalence or complete a migration; the separate local planner performs source-bound proposal work.
Inputs: python_sdk (required), native_model (required), source_shape (required), schema_version (required), +4 more.
oruk_transcribe_audioTranscribe audioARead-onlyInspect
Transcribe prerecorded English audio to text with time-ordered segments and word timings. Use this when only the words matter. Accepts wav/flac/mp3/m4a/ogg/webm. Up to 30 MB via audio_url or 8 MiB decoded via audio_base64; up to 60 minutes of English speech. Does not score emotion or tone — use oruk_analyze_speech for transcript + tone together, or oruk_analyze_tone for tone alone.
Inputs: model, detail, api_key, diarize, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Transcribe audio & video to text for AI agents: 100+ languages, speaker labels, webhooks.
STT + SRT/VTT; 3-hour async jobs; dTelecom-compatible file API; x402 $0.005/min, no prepaid credits
Let AI agents make phone calls and join Zoom, Teams and Google Meet meetings. Hosted or self-hosted.
English WAV transcription on a GPU. No login: agents obtain temporary trial access automatically.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables AI agents to use speech AI capabilities including LLM chat completions, text-to-speech in Uzbek, Russian, and English, speech-to-text transcription with speaker labels, voice isolation for noise removal, and realtime WebSocket streaming.MIT
AssemblyAI MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables MCP-capable agents to submit and retrieve audio transcriptions, apply speech understanding such as translation, speaker identification, summaries and action items, and enforce guardrails including PII redaction and content moderation.2MIT- FlicenseNot gradedqualityBmaintenanceEnables MCP-compliant agents to analyze speech prosody and vocal sentiment from audio-derived input, measuring speech rate, pitch variance, and user cognitive fatigue. Exposes these deterministic results over JSON-RPC so clients can dynamically calibrate their response pacing.7-
- AlicenseNot gradedqualityAmaintenanceRecords your calls on your own computer, transcribes them on the machine, and lets an agent start, follow, question and annotate a call while it runs. No meeting bot, no account and no cloud; the same core runs as a self-hosted transcription server.20GPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.