Fran

research eng @elevenlabsio

[Fran @FranekMirko]

@willdepue joined ElevenLabs at 16yo, fulltime, dropped high school, helped take low-latency/on-device TTS models from scratch to signed deals. Would looveee to join if there’s a chance!!

[Fran @FranekMirko]

@willdepue DM’d! Joined ElevenLabs at 16yo, helped take low-latency/on-device TTS models from scratch to signed deals. Would looveee to join!!

[Fran @FranekMirko]

@willdepue DM’d! Joined ElevenLabs at 16yo, helped take low-latency/on-device TTS models from scratch to signed deals. Would looveee to join!!

[Fran @FranekMirko]

@xf1280 Great, so let’s now run the most basic tasks with 3 trillion-parameter models

[Fran @FranekMirko]

@ID_AA_Carmack robotics is also largely a model problem, so isn't saying SI is more likely to develop humanity-enslaving system than capable robot brain very silly? it could just solve this as any other task and doom

[Artificial Analysis @ArtificialAnlys]

ElevenLabs' Eleven v4 Turbo takes the #1 spot on the Artificial Analysis Provider Voice TTS Arena Leaderboard, ahead of Eleven v4 while costing half the price

Eleven v4 Turbo is the faster, lower-cost sibling of Eleven v4 from @ElevenLabs, designed to deliver comparable speech quality with lower latency and cost.

Key takeaways:

➤ Provider Voice: Eleven v4 Turbo has an Elo of 1,334 (+19/-19) across 1,645 appearances, placing it ahead of Eleven v4 at 1,321, Alibaba's Qwen-Audio-3.1-TTS-Plus at 1,292 and Cartesia's Sonic 3.6 at 1,278. It ranks #1 in Customer Service and Entertainment and #2 in Assistants and Knowledge Sharing.

➤ Controlled Voice: Eleven v4 Turbo ranks #2 with an Elo of 1,173 (+15/-15) across 1,745 appearances, behind Qwen-Audio-3.1-TTS-Plus at 1,181 and ahead of Eleven v4 at 1,160. It ranks #1 in Arabic, German, Hindi and English (UK).

➤ Pronunciation Robustness: Eleven v4 Turbo scores 90.1%, ranking #2 behind Eleven v4 at 91.7% and ahead of Gemini 3.8 Flash TTS at 89.5%.

➤ Pricing: Eleven v4 Turbo is priced at $40/1M characters, half the price of Eleven v4 at $80/1M characters, compared to Sonic 3.6 at $49/1M characters and Gemini 3.8 Flash TTS at $16.49/1M characters.

➤ Speed: Eleven v4 Turbo processes 96 characters per second of generation time, compared to 84 characters per second for Eleven v4 and 59 for Eleven v3.

See more details and listen to samples below 🧵

[Krzysztof Olipra @KrzysztofOlipra]

It’s always been called SI in Polish.

We’re so ahead of the curve.

[Mati Staniszewski @mati]

Thrilled to have @JensenHuang join us at ElevenLabs Summit on 11/11 in NYC!

NVIDIA has been a great partner since our earliest days, all the way back to 2022 (!) - and excited to now have Jensen join us on stage to discuss what's ahead for voice AI & agents!

See you in NYC!

[Fran @FranekMirko]

🔥🔥

[Mati Staniszewski @mati]

We just closed an employee tender offer which values @ElevenLabs at $22BN, up 2x from our Series D in February. The tender was led by Wellington and T. Rowe Price.

A few words on how we got here ↓

[Mati Staniszewski @mati]

We just closed an employee tender offer which values @ElevenLabs at $22BN, up 2x from our Series D in February. The tender was led by Wellington and T. Rowe Price.

A few words on how we got here ↓

[Hubert Siuzdak @HubertSiuzdak]

It's been super fun pushing what's possible with on-device TTS with such a great team. So proud of what we've built - and sharing it at our Summit in Warsaw, where ElevenLabs began, feels pretty special. 🇵🇱

[Hubert Siuzdak @HubertSiuzdak]

We've had a lot of fun with Eleven v4. The level of realism keeps surprising us, and we think you'll have fun with it too.

At the same time, it's incredibly practical, leading in pronunciation robustness and human preference.

[Fran @FranekMirko]

Great model, both best-of-n and worst-of-n performance vastly improved in all domains of audio!

[ElevenLabs @ElevenLabs]

Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.

Ranked #1 by Artificial Analysis.

[Fran @FranekMirko]

@ElevenLabs let's gooo

[ElevenLabs Developers @ElevenLabsDevs]

Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.

Ranked #1 by Artificial Analysis, Eleven v4 delivers the most expressive results for developers building creative experiences, while Eleven v4 Turbo is optimized for real-time voice agents.

[Piotr Dabkowski @dabkowski_piotr]

A couple of things that make Eleven v4 special:

- Extremely low latency (100 ms p50 TTFB for Turbo)
- By far the best voice similarity
- Outstanding quality (#1 on Artificial Analysis and on our own benchmarks)

It achieves all of this while being extremely reliable. Eleven v4 uses our new post-training stack and a surprising recent research discovery that we hope will greatly accelerate our future model development.

By the end of the year, we expect delivery of new compute that will increase our training capacity almost 10x. Very excited for what's ahead!

Congratulations to the team!

[ElevenLabs @ElevenLabs]

Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.

Ranked #1 by Artificial Analysis.

[Fran @FranekMirko]

@ahadj0 with 27x compression aren't the latent action codes like a few Hz? In absolute terms - isn't that a big bottleneck for the policy too?