Give an agent access to speech assessment as a tool instead of embedding pronunciation logic in every prompt. The MCP server returns structured evidence your orchestration layer can inspect, explain and act on.
The agent selects an assessment tool, supplies the audio and reference context, then receives a result designed for downstream reasoning.
Chivox scores speech, your application enforces product rules, and the LLM turns approved evidence into a useful response.
The quickstart is intentionally small, while the surrounding runtime covers authentication, usage controls, observability and deployment choices.
All three use the same Chivox speech-assessment capability. The right choice depends on who captures the audio, who decides to score, and how much of the loop your application controls.
| Compare | SDK & API Native scoring inside the product you own. | MCP server Standardized tool layer for compatible clients. | Function calling Typed function inside your own agent stack. |
|---|---|---|---|
| Best-fit scenario | Embed speech assessment inside a learner-facing app or education platform you own. | Expose the same speech tools to MCP-compatible clients and agent environments. | Add speech assessment inside a custom voice agent or an existing LLM workflow. |
| Best-fit teams | EdTech product teams, mobile/web engineers, and platforms that capture audio in-product. | Developer-tool teams, platform teams, and products supporting several MCP clients. | Voice-agent teams, AI application engineers, and product teams with their own orchestration layer. |
| Integration style | Native SDK plus REST/WebSocket — your code starts the session and owns the UX. | Configure one standardized MCP server that publishes discoverable assessment tools. | Define and invoke a typed function contract in your chosen model or agent SDK. |
| Portability | Highest inside your own product surfaces (iOS, Android, web, server); not an agent tool protocol. | Higher across compatible MCP clients; the tool definition stays consistent. | Depends on the provider or framework, but fits deeply into a custom application loop. |
| Application control | Your application controls capture, when to score, thresholds, retries and learner feedback. | The client discovers and calls tools while your server controls assessment behavior and output. | Your application directly controls validation, routing, retries, thresholds, and response handling. |
| Choose it when… | You own the learner journey and need scoring embedded directly in the product UI. | You want the fastest reusable path into MCP ecosystems or need one tool layer for several clients. | You already own the agent loop and need precise control over when and how assessment runs. |
Paste this into Cursor, Windsurf, Zed or any client that speaks streamable HTTP — nothing to install. Your LLM immediately sees all 16 assessment tools and starts getting structured scores back.
{
"mcpServers": {
"chivox": {
"type": "streamable-http",
"url": "https://mcp-global.cloud.chivox.com",
"headers": { "Authorization": "Bearer <your_api_key>" }
}
}
}The model chooses the tool, Chivox returns deterministic speech evidence, and your application controls the approved response.
The MCP client discovers 16 assessment tools and picks the one that fits the turn — no routing code on your side.
Pronunciation, fluency and integrity are scored against the reference text, with per-word and per-phoneme detail.
The result is deterministic JSON: the same audio and reference always produce the same fields.
The LLM explains only the fields your application approves — thresholds stay in your product logic.
MCP is an agent-friendly integration layer around the assessment capability. Teams can choose the integration pattern that best fits their architecture.
The response is structured data. Your orchestration layer can pass selected fields to the model or use them in deterministic product logic.
Tell us what you’re building and whether you need SDK/API, MCP, or function calling. We’ll reply within one business day with pilot credits, pricing, or a deployment plan.