Eleven v3 is out of alpha and ready for commercial use.
Since alpha, we've improved stability and accuracy:
- Stability: more reliable model and higher user preference scores
- Accuracy: 68% fewer errors on numbers, symbols, and technical notation
We’ve partnered with @LTXStudio to bring their new Audio-to-Video model exclusively to ElevenLabs.
For the next 7 days, generate audio-first videos exclusively on the ElevenLabs Creative Platform.
$1,111 up for grabs for developers building with Scribe v2.
Build a real-world product using our most accurate Speech to Text model and show what production-grade transcription can do.
Today we’re introducing Scribe v2: the most accurate transcription model ever released.
While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.
@dmwlff Can't agree anymore. the boiler code, and boring code review keep draining me in my career. i can't believe requirement could be fun again nowaday lol