ElevenLabs Developers

Deploy natural, human-sounding agents with the @ElevenLabs AI audio platform. For status updates, see

[ElevenLabs Developers @ElevenLabsDevs]

Add them to your agent with one command:
> npx skills add elevenlabs/skills

And all are open source: https://t.co/C89VdkWcIp

[ElevenLabs Developers @ElevenLabsDevs]

ElevenLabs Skills just crossed 40,000 installs.

Use them to build apps with Text to Speech, Speech to Text, ElevenAgents, Music, Sound Effects, Voice Isolation, and more.

[ElevenLabs Developers @ElevenLabsDevs]

Generated with ElevenLabs.

[Victor M @victormustar]

Asked Kimi K3 for "The Odyssey in ASCII" (didn't expect the arrow scenes 👌)

[superwhisper @superwhisper]

We added @ElevenLabs Scribe v2 Realtime to Superwhisper a few months ago. It's now one of our most-used models✨

Read here: https://t.co/ZCSXLaWwEg

[ElevenLabs Developers @ElevenLabsDevs]

What is your most used API?

[ElevenLabs Developers @ElevenLabsDevs]

Accidentally building self-aware NPCs. Part 3.

[Rosebud AI @Rosebud_AI]

@Erling would love this. Music and SFX are at the center of this football game.

Made entirely on @Rosebud_AI with the new @ElevenLabs API integration for audio.

[ElevenLabs Developers @ElevenLabsDevs]

Add Voice to your AI Agents

[ElevenLabs Developers @ElevenLabsDevs]

https://t.co/vCVZR1VKBU

[ElevenLabs Developers @ElevenLabsDevs]

Building agentic NPCs in Unity. Part 2.

[ElevenLabs Developers @ElevenLabsDevs]

Accidentally building self-aware NPCs

[ElevenLabs Developers @ElevenLabsDevs]

https://t.co/vCVZR1VKBU

[ElevenLabs Developers @ElevenLabsDevs]

NPCs you can talk to.

We are working on a Unity SDK so you can add real-time voice agents to your games. Here is an early look.

[Yash @dew_yashtwt]

cooking something

working on voice agent mode for @supercodeai

feels insanely fast and way too good for a v1

@ElevenLabs @ElevenLabsDevs

[Udayan Walvekar @udayan_w]

🌍 World’s Largest Hermes Buildathon
10 cities. 5 countries. $750K credits

Backed by OpenAI, Convex, Cloudflare, ElevenLabs, Linkup, Dodo Payments, Hissa Fund & Wispr Flow. Proudly presented by GrowthX.

Hermes is the fastest growing AI agent in 2026 (Open Source). Millions of developers are obsessed with it, and so are we.

Happening across

- San Francisco
- Paris
- Singapore
- Jaipur
- Delhi
- Mumbai
- Pune
- London
- Hyderabad
- & Bengaluru

Who are your hosts?

In Bengaluru,
we have Kshitij, Engineer @NousResearch, @AshikkaG (Founding Engineer @ Rapidflare) & Pranav (Tech Lead @ GrowthX). Hosted at the awesome @Razorpay

In San Francisco, we have
Kishan (Sr. Engineering Manager @ Okta), Saloni (Growth @ Tandem AI, ex Antler, Inmobi) & Udayan (Yup! I am co-hosting SF)

In Mumbai, we have
Prathamesh ( Head of AI @ NotYourIdea), Apoorva (AVP @ Angel One) & Jaimit (Founder @ Metuzi AI, ex CMO @ Lenskart)

In Delhi, we have
Anupam (CEO @ Digia, ex Engineering leader at Urban Company) & Nishkarsh Bansal (Head of Product and AI at YC-backed AppX)

In Paris, we have
@satvikputi (Product @ Stairling, Ambassador Lovable, ex Opella)

In Pune, we have
Two Rahuls :).. Rahul (Lead, Data Science @ Mindstix), Rahul (Tech @ Cadence)

In Singapore, we have
Ayan (AI Product Lead @ Afresh), Ayushi (Growth Head @ Aramya, backed by Accel & Matrix)

In Hyderabad, we have
Akhilesh (Director of AI @ Altir), Hitesh (Founder @ Motor360, ex Engineering Manager @ Gainsight)

In Jaipur, we have
Prateek (Tech lead @ Red Hat), Surbhi (ex Engineering Director @ Glance).

In London, we have
Yogi (Partnerships @ Canva; 103 partnerships including NVIDIA, Stripe, and Google)

Whether you're in the US, India, Singapore, Europe, or the UK. Across 5 time zones, there's a room near you.

Who is this for?
AI-first engineers
Founders
Product leads
Growth engineers
Forward deployed engineers
GTM and growth operators

Registrations close in 72 hours.

[ElevenLabs Developers @ElevenLabsDevs]

ElevenLabs in 100 Seconds

[ElevenLabs Developers @ElevenLabsDevs]

Full guide: https://t.co/HJyTIjAqTu

[ElevenLabs Developers @ElevenLabsDevs]

Speech Engine now supports @pipecat_ai.

Run a Pipecat pipeline as the LLM brain behind your voice agent. Speech Engine handles the voice loop, Speech to Text, turn-taking, and Text to Speech, while Pipecat handles text generation.

[ElevenLabs Developers @ElevenLabsDevs]

The Pipecat pipeline runs as the LLM brain inside Speech Engine.

The Speech Engine SDK runs as the outer layer. The on_transcript callback fires every time the user finishes speaking. Inside the callback, you build a Pipecat pipeline, feed the conversation history in as an LLMContextFrame, and stream the pipeline’s text output back to Speech Engine.

ElevenLabs converts the text to speech and plays it to the user.

[ElevenLabs Developers @ElevenLabsDevs]

Full walkthrough with the worker code, token server, and audio format reference: https://t.co/dCEmlR7pzt

[ElevenLabs Developers @ElevenLabsDevs]

Speech Engine now supports @livekit.

A LiveKit Agents worker joins the room, subscribes to the user's audio, streams it to Speech Engine, and publishes the synthesized response back as its own track.

[ElevenLabs Developers @ElevenLabsDevs]

Python and Node are both supported. We recommend the Python worker for production. The Node bridge depends on LiveKit’s @livekit/rtc-node SDK, which LiveKit currently labels as Developer Preview.

Only need a browser-to-agent voice with no other participants? Use Speech Engine with WebRTC, which is simpler.