ElevenLabs launches Eleven Realtime speech-to-speech models
10/21/2026 — 10/21, 14:18·2 sources (all)·2 reports (all)
Key takeaways
- ElevenLabs has launched Eleven Realtime, a pair of speech-to-speech models. v1 Max scores 98.8% on Big Bench Audio with 0.57-second latency,…
Background & analysis
On October 21, 2026, ElevenLabs released two speech-to-speech models under the name Eleven Realtime, according to The Decoder. The larger variant, v1 Max, scores 98.8% on the Big Bench Audio benchmark with a response time of 0.57 seconds. ElevenLabs says that no model currently on the Artificial Analysis leaderboard is both faster and more accurate. The smaller v1 Mini targets natural conversation at lower cost and is able to tell when the other speaker has finished talking. Both models are offered through the ElevenAgents platform and through an API compatible with OpenAI Realtime, and are billed by the minute plus tokens. The available reporting covers the launch and specifications only; no further developments have been reported.
AI-generated from 1 reports · updated 12 hours ago
Latest turnAccording to TestingCatalog, ElevenLabs has released two speech-to-speech models. Eleven Realtime v1 Max scores 98.8% on Big Bench Audio and starts speaking in 0.57 seconds, while Mini is tuned for natural conversation at low cost. Both models are available now.
Related AI tools
- Heat index
- 164
- All sources
- 2
- All reports
- 2
- First seen
- 13 hours ago
Reports on this story headlines open the original
According to TestingCatalog, ElevenLabs has released two speech-to-speech models. Eleven Realtime v1 Max scores 98.8% on Big Bench Audio and starts speaking in 0.57 seconds, while Mini is tuned for natural conversation at low cost. Both models are available now.
X：TestingCatalog (@testingcatalog)AI score 57The Decoder reports that ElevenLabs has released two speech-to-speech models, Eleven Realtime. The v1 Max variant scores 98.8% on Big Bench Audio with a 0.57-second response time, and the company says no model on the Artificial Analysis leaderboard is both faster and more accurate. The smaller v1 Mini targets low-cost natural conversations and can tell when someone has finished speaking. Both are available through the ElevenAgents platform and an OpenAI-compatible Realtime API.
The DecoderAI score 62
Other stories people are talking about
- Heat index 71Tutorial adds AI voice narration to WordPress posts with ElevenLabs1 sources
- Heat index 801DHS orders federal civilian agencies to purge DeepSeek tech17 sources
- Heat index 795RisingDeepSeek open-sources DeepInfer large-scale inference framework14 sources
- Heat index 735RisingMiniMax launches M3.1 Flash with 70% lower Agent costs18 sources
- Heat index 698RisingSpaceX earnings call: Musk says 2027 ARR could reach $1 trillion9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion