When I was in kindergarten, we wrote letters to our future selves to read when we turned 25. Today I opened that letter from Mrs. Hirano’s class… Kids say the darndest things

Introducing Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and

Stem Separation ✅ In-Painting ✅ Halloween music banger ✅✅✅

Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.

One of the best things about working at ElevenLabs - teams across the company dropping incredible product updates every week. Now anyone can make high quality audio/video content.

Today, @elevenlabsio is launching a $100M employee tender co-led by Sequoia & ICONIQ at a $6.6B valuation - 2x since Series C just 9 months ago. With ARR >$200M in <3 years and enterprise adoption surging, we’re aligning the team for long term while helping them realize value now

The wait is over for @elevenlabsio Music. Generate studio-quality songs, in any genre or style, using natural language prompts. My prompt for this video's soundtrack: "Upbeat alternative rock track (~110–120 BPM) with crunchy but clean electric guitars, solid bass, and energetic

Introducing Eleven Music. The highest quality AI music model. - Complete control over genre, style, and structure - Multi-lingual, including English, Spanish, German, Japanese and more - Edit the sound and lyrics of individual sections or the whole song

(3) There has never been a robotic sounding ElevenLabs voice. And there never will be.

(2) If you needed to be heard everywhere tomorrow, you'd choose ElevenLabs.

My favorite vintage watch ads reimagined for @elevenlabsio Just like the greats, we care about quality craftsmanship, sensory luxury, and performance that holds up under pressure. (1) We built the ElevenLabs API for the moments that can’t buffer.

Never a dull day on X dot com, the everything app (from the new @elevenlabsio v3 + @hedra_labs)

Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever. Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.

A big day today: we teamed up with Epic Games to bring Darth Vader’s voice to Fortnite. Millions of players can now speak with Vader in real time. Live voice interactions like this will become the new standard in gaming.

We still don’t know exactly how human consciousness evolved - and whether it could emerge in AI is just as fascinating. You can now talk with Charles Darwin about it: +1 (410) 6DARWIN.

They don’t want you to know you can watch White Lotus while an army of @Fern_Labs agents builds your weekend project

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support

Hello, World! Follow for changelog updates, developer community spotlights, tutorials, tips, and more! Start here: https://t.co/85tFFTOgpX

We’ve raised a $180M Series C to give every AI agent a voice. The past year has been about building the foundations of AI audio - now we’re focused on making speech the standard for how we interact with technology.

Thanks for the ElevenLabs shoutout, @lexfridman! Loved working together to bring your conversation with President Zelenskyy to multiple languages, while maintaining his authentic voice and delivery.

If you want to recreate my work, you can check out our docs: https://t.co/KEORrp8YL4 You can give your agent the power to make updates to your browser with Client Tools: