ElevenLabs officially launched its new voice-first AI personal assistant, 11ai, marking another major breakthrough in voice AI technology within the productivity tools field. As a company known for innovative text-to-speech and conversational AI technologies, ElevenLabs' newly released 11ai not only integrates cutting-edge voice interaction features but also provides users with a highly personalized workflow experience through multi-tool integration and customizable MCP (Multi-Channel Protocol) support.

image.png

Voice-First, Productivity-Centric

11ai is designed with voice interaction at its core, aiming to improve user efficiency through natural and smooth conversations. According to ElevenLabs' official introduction, 11ai supports over 5,000 voices, and users can even customize their own unique voice, making the assistant more personalized. Whether it's scheduling, handling messages, or executing complex workflows, 11ai can respond quickly through voice commands, truly achieving the experience of "conversing with a real person."

Its core features include:

Calendar Management: Seamlessly syncs with Notion or Google Calendar, easily planning daily tasks.

Real-Time Search: By integrating Perplexity, users can directly query online information through voice, quickly obtaining research or potential customer leads.

Team Collaboration: Supports deep integration with tools like Slack and Linear, allowing users to send messages or submit issue tickets through voice.

This series of features makes 11ai not only suitable for individual users, but also an ideal choice for enterprise teams to enhance collaboration efficiency.

MCP Support, Unlocking Infinite Customization Possibilities

Another highlight of 11ai is its support for MCP (Multi-Channel Protocol). Users can build custom workflows by creating their own MCP, seamlessly connecting 11ai with existing tools or private servers. For example, developers can use MCP to integrate 11ai into internal enterprise systems, enabling automated operations from voice control to data processing. This feature greatly expands the application scenarios of 11ai, making it equally versatile as both a personal productivity tool and an enterprise-level solution.

In addition, 11ai's multimodal interaction capabilities are impressive. Users can freely switch between voice and text input, and the system ensures the coherence and accuracy of conversation context through built-in RAG (Retrieval-Augmented Generation) technology, especially suitable for scenarios requiring quick handling of complex tasks.

Multi-Language and Cultural Adaptation, Targeting the Global Market

As a company renowned for multilingual support, ElevenLabs continues its global vision in 11ai. 11ai supports over 70 languages and has an automatic language detection function that dynamically adjusts voice output based on user input. Combined with the previously released Eleven v3 model, 11ai's voice generation is not only natural and smooth but also allows control over emotions, tone, and even non-verbal expressions (such as laughter or whispers) through audio tags, providing strong technical support for cross-cultural communication.

This feature gives 11ai great potential for application in global markets, especially in education, entertainment, and customer service sectors, where 11ai is expected to become an important bridge connecting users of different languages.