close
close

Apre-salomemanzo

Breaking: Beyond Headlines!

    • ElevenLabs now offers the ability to create conversational AI agents
    aecifo

    ElevenLabs now offers the ability to create conversational AI agents

    Umito Posted on

    ElevenLabsa startup that offers AI voice cloning and a text-to-speech API, launched the ability to create conversational AI bots on Monday.

    The company announced that users can now create full-featured chatbots on the ElevenLabs development platform, with customizable variables such as tone of voice and response length.

    ElevenLabs has mainly worked on providing different voices and AI tools for text-to-speech services. The company’s head of growth, Sam Sklar, told TechCrunch that many of its customers are already using this capability to create conversational AI agents. However, the most difficult parts were integrating the knowledge base and dealing with customer outages. That’s why the company decided to create a complete pipeline for conversational bots.

    Users can log in to their ElevenLabs account and start creating a chat agent by selecting a template or creating a new project. They can choose the agent’s primary language, first message, and system prompt to determine the agent’s character. Developers must also select a major language model (Gemini, GPT, or Claude), response temperature (to determine how creative the response is), and token usage limit.

    They can also adjust other aspects such as voice, latency, stability, authentication criteria and maximum conversation time with the AI ​​agent.

    Users can add their own knowledge base, such as a file, URL or block of text, to populate the chatbot. Additionally, they can also integrate their own personalized LLM into the bot. The ElevenLabs SDK is compatible with Python, Javascript, React and Swift. The company also offers a WebSocket API for more customization.

    Businesses can also define criteria to collect certain data elements (for example, the name and email address of customers speaking to the agent), as well as natural language evaluation criteria to define success or the failure of the call.

    ElevenLabs leverages its existing pipeline for the speech synthesis part. The company needs to develop text-to-speech capabilities for the new conversational AI product. The company does not yet offer its text-to-speech API as a standalone product, but it may do so in the future, making it a competitor to Google, Microsoft, and Amazon’s text-to-speech APIs, as well as specialized APIs . APIs, such as The whisper of OpenAI, AssemblyAI, Deepgram, Speechmatics And Gladie.

    The company, which aims to raise new funds at a valuation north of $3 billionalso competes with other voice AI startups, such as Vapi And Tell – they also build conversational agents. Most notably, the company will also compete OpenAI’s real-time conversational API. However, ElevenLabs believes that its customizations and ability to change models will give it an advantage over OpenAI.

    Umito
    View all posts

    You Might Also Like