ElevenLabs

Europe is ARR maxxing Still remember being on early due diligence calls with some of the first investors 😂 They wanted to know if elevenlabs was good… I basically said “don’t sleep on it” t.co/7N59y2nlAB

ElevenLabs has just dropped SFX v2 ✨ You can create professional 48kHz sound effects from just text. 30 seconds, infinite looping, royalty free and much more. I've made you some examples to check below + how to try it out There are so many categories, and you can just prompt your way to ANY sound, but to give you an idea, there is a bunch of categorised sounds. Devices Prompt examples: "vintage radio, frequency change, interference, radio static" "digital data transfering" "Ring phone" Braams Prompt examples: "huge braam, terrifying, tension" "dark, violent energy building up, creating a reverberating effect" "Epic cinematic braam horn" Keys Prompt examples: "Lofi keys, piano" "Rhodes keyboard, experimental sound design, ambient" "Wurlitzer keys" UI-Elements: Prompt examples: "A modern digital confirmation sound, short and clean, soft electronic beep with a pleasant tone, symbolizing successful task completion, like a check mark notification" "Tiny “ding!” chime" "subtle chime" Whooses: Prompt examples: "Whoosh" "big whoosh" "long whoosh" "strong whoosh" Foley: Prompt examples: "Footsteps walking" "fart" "Door knocking" "kick a can" That took a moment, I hand selected each sound you heard in each of the videos, and edited each of the videos with the sounds in the order I felt make since to highlight each category. For me having access to 48kHz in wav is a game changer for sure. The extra 8 seconds also helps a lot with soundscapes and longer loops x.com/elevenlabsio/status/1… It's darn simple, you go here: elevenlabs.io/sound-effects Give it a go, free to try it out.

Eleven v3 is available now at and is 80% off in the app UI for the month of June. elevenlabs.io/v3

A quote from Mati Staniszewski, Co-Founder & CEO, ElevenLabs (enacted by AI)

According to Elevenlabs this is why v3 stands out: 👉 70+ languages: Expanding from 33, covering 90% of the worlds population. 👉 Dialog mode: Handles natural interruptions, tone shifts, and emotional flow. 👉 Audio tags: Guide delivery with tags like [whispers], [angry], [laughs], or [door creaks]—controlling performance in fine detail. 👉 Text to dialog API: Purpose-built for multi-speaker generation in interactive media. 👉 Instantly available: test it right now 🤣 👉 Streaming support coming soon: Coming soon for call centers and real-time conversational agents.

v3 was designed not just to read, but to perform! Built on a new architecture, Eleven v3 brings unprecedented realism and control to speech generation It can shift tone mid-sentence, moves seamlessly between characters, & responds to cues like [whispers], [laughs], and [sighs]

Now imagine a pipeline where you use gemini to intemperate whats going on in any sports event. That feeds into elevenlabs, with prompt cues on where to have emotions, expressive shout outs etc. You'll basically have infinite commentators in 70+ languages (up from 33)

Natural sounding voice, that is indistinguishable from humans might just be a few months away. We are so close now. But the thing is, once we get there, we have arrived, there is not another level. Once reached, we've arrived v3 deeply understands text, that results in this

To be clear, it's still an Alpha, and it requires more prompting engineering to get great results. But if you are putting in the extra work, the output simply speaks for itself, these outputs are so lifelike, so real. Close your eyes, and just listen

I'm speechless... This is a major step-change in AI generated voice (TTS) Elevenlabs just released v3 as a public alpha and you can try it now for 80% off during all of June 💸 Let's unpack this 👇