Speech
Hosted speech-to-text + speech emotion/tone analysis for agents. No install; trial keys built in.
- Transport
- Not stated
- Package
- —
- Registry id
- ai.oruk/speech
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
The hosted oruk MCP server turns transcription and speech emotion/tone analysis into tools your coding agent can call. It works without an API key for docs, models, and trial keys, and full access requires adding a key as an Authorization: Bearer header. It offers self-serve plans that start with a 7-day free trial.
Audio input is accepted as a public URL up to 30 MB or base64 bytes up to 8 MiB decoded, supporting wav, flac, mp3, m4a, ogg, or webm formats. It processes up to 60 minutes of English speech. It provides tools like oruk_analyze_speech, which returns transcript, emotion, and speaking-style scores in one call.
It allows creating a trial key without an account, giving a 30-minute key with 3 free requests. The HTTP endpoint supports MCP protocol versions 2026-07-28, 2025-03-26, 2025-06-18, and 2025-11-25.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.