Topics

Latest

AI

Amazon

Article image

Image Credits:ElevenLabs

Apps

Biotech & Health

clime

ElevenLabs

Image Credits:ElevenLabs

Cloud Computing

Commerce

Crypto

enterprisingness

EVs

Fintech

fund-raise

gismo

Gaming

Google

Government & Policy

Hardware

Instagram

Layoffs

Media & Entertainment

Meta

Microsoft

Privacy

Robotics

Security

societal

Space

startup

TikTok

transport

Venture

More from TechCrunch

Events

Startup Battlefield

StrictlyVC

Podcasts

picture

Partner Content

TechCrunch Brand Studio

Crunchboard

Contact Us

ElevenLabs , a startup that provides AI part cloning and a textual matter - to - spoken language API , launch the power to build conversational AI bots on Monday .

The company announced that users can now build complete colloquial agents on ElevenLabs ’ developer platform , with customizable variables such as tone of voice and response length .

ElevenLabs has mostly worked on providing dissimilar vocalism and AI tools for school text - to - talking to overhaul . The company ’s head of growth , Sam Sklar , told TechCrunch that many of its clients were already using this power to create conversational AI agents . However , the toughest parts were integrate the knowledge base and plow break from customer . That ’s why the company decided to build a full line for colloquial bots .

Users can log into their ElevenLabs report and bulge build a conversation broker by selecting a guide or creating a new projection . They can select the agent ’s main language , first subject matter , and system prompt to determine the agent ’s role . Developers also have to take a large linguistic communication manikin ( Gemini , GPT , or Claude ) , the temperature of responses ( to determine how creative the response should be ) , and token usage boundary .

They can also tune up other aspects like vocalization , response time , stability , authentication criteria , and maximal distance of conversation with the AI agent .

Users can bestow their own knowledge base , like a file , URL , or textbook cube , to power the colloquial bot . Plus , they can = integrate their own tradition LLM with the bot . ElevenLabs ’ SDK is compatible with Python , JavaScript , React , and fleet . The fellowship also offers a WebSocket API for more customization .

Companies can also define criteria to hoard sure data point point — for instance , name and e-mail of customers speaking to the agentive role —   along with rating criteria in natural language to define the success or bankruptcy of the call .

Join us at TechCrunch Sessions: AI

Exhibit at TechCrunch Sessions: AI

ElevenLabs is leverage its live pipeline for the text - to - voice communication part . The fellowship has to develop speech - to - textbook capabilities for the new conversational AI product . The company is not offering its oral communication - to - text API as a digest - alone product as of now , but it might do that in the futurity , seduce it a competitor to Google ’s , Microsoft ’s , and Amazon ’s speech - to - text APIs , as well as specialised APIs , such asOpenAI ’s Whisper , AssemblyAI , Deepgram , SpeechmaticsandGladia .

The fellowship , which is aim to raise novel funding ata valuation north of $ 3 billion , also competes with other voice AI startup , such asVapiandRetell —   they are also building conversational agents . More notably , the company will rivalOpenAI ’s real - sentence conversational API . However , ElevenLabs believes that its customizations and ability to switch models will give it an edge over OpenAI .