# AIVOCO models

## Docs

- [Open Source S2S Benchmark ](https://docs.aivoco.com/Benchmarks/rosebench.md): An open-source benchmarking and evaluation framework for Speech-to-Speech (S2S) AI models, designed by AIvoco to assess end-to-end model capabilities across latency, speech naturalness, response accuracy, memory retention, and conversational fluidity. The framework enables researchers and developers…
- [Languages Supported](https://docs.aivoco.com/Models/languages.md): Explore the 200+ global and regional languages supported by the AIVOCO Speech-to-Speech model.
- [Rose](https://docs.aivoco.com/Models/rose.md): Discover ROSE, AIvoco's 250 billion parameter Speech-to-Speech model, revolutionizing real-time voice AI agents with human-like interactions and seamless telephony integration.
- [Vision](https://docs.aivoco.com/Models/vision.md): Discover Vision, AIvoco's groundbreaking multimodal LLM, enabling continuous learning, long-term memory, and personalized AI clones for a new era of autonomous digital employees.
- [Agents](https://docs.aivoco.com/Speech-to-Speech/agents.md)
- [Connect](https://docs.aivoco.com/Speech-to-Speech/connect.md)
- [Functioncalling](https://docs.aivoco.com/Speech-to-Speech/functioncalling.md)
- [Overview](https://docs.aivoco.com/Speech-to-Speech/overview.md)
- [Transcription](https://docs.aivoco.com/Speech-to-Speech/transcription.md)
- [Inbound](https://docs.aivoco.com/Telephony/Inbound.md): The Inbound URL allows telephony platforms to seamlessly route incoming calls directly into the ROSE Speech-to-Speech (S2S) system.   We’ve built a universal endpoint that supports configuration for multiple telephony providers  meaning you can connect your existing setup (Twilio, Telnyx, Exotel, et…
- [Outbound](https://docs.aivoco.com/Telephony/Outbound.md): Learn how to connect your ROSE speech-to-speech WebSocket to Twilio for outbound calls or your own telephony infrastructure.
- [Connect Agent](https://docs.aivoco.com/api-reference/endpoint/connect.md): Establish a two-way real-time speech-to-speech WebSocket connection with your AI agent.
- [Create Agent](https://docs.aivoco.com/api-reference/endpoint/create.md)
- [Delete Agent](https://docs.aivoco.com/api-reference/endpoint/delete.md)
- [Function Calling](https://docs.aivoco.com/api-reference/endpoint/functioncall.md)
- [List Agents](https://docs.aivoco.com/api-reference/endpoint/get.md)
- [Transcribe Audio](https://docs.aivoco.com/api-reference/endpoint/transcription.md): Transcribes audio using Vispark Transcription API.
- [Update Agent](https://docs.aivoco.com/api-reference/endpoint/update.md)
- [Introduction](https://docs.aivoco.com/api-reference/introduction.md): Get started with ROSE, our real-time Speech-to-Speech (S2S) agent creation API.
- [Development](https://docs.aivoco.com/development.md): Learn how to develop and test your speech-to-speech agents using AIVOCO’s APIs and WebSocket connections.
- [Introduction](https://docs.aivoco.com/index.md): Welcome to AIVOCO's Speech-to-Speech API documentation
- [Quickstart](https://docs.aivoco.com/quickstart.md): Start building your first Speech-to-Speech Voice AI Agent with AIVOCO

## OpenAPI Specs

- [openapi](https://docs.aivoco.com/api-reference/openapi.json)

## Optional

- [Blog](https://www.aivoco.com/blogs.html)