In November we announced our new, fastest model that generates speech at ≈400ms latency (+ network latency) and is over twice as fast as our V1 models.
Unfortunately users found that it struggled to pronounce long numbers. Give a listen to this generation of "The current stock price for NVIDIA is $867.49.":
Today we just released improved numbers pronunciation for our Turbo v2 model. Here's pronunciation after the change:
Thank you to all of the users who submitted feedback that inspired this fix - and please continue to share areas where our models can be improved.
.webp&w=3840&q=95)
At the ElevenLabs London Hackathon, developers created GibberLink, a groundbreaking protocol that lets AI agents recognize each other and switch to a hyper-efficient sound-based language—making AI-to-AI communication 80% faster and more reliable.
The fastest, zero-cost way to create and distribute audiobooks globally
