ElevenLabs Expands Generative Audio Platform with Voice Isolation, Sound Effects, and Multi-Speaker Podcast Generation

ElevenLabs unveils new voice isolation technology, AI sound effects generation, and a complete multi-speaker podcast creation studio.

Tuesday June 2, 2026 Source: elevenlabs.io
TL;DR — Quick Answer

ElevenLabs has expanded its generative audio platform with new capabilities spanning voice isolation, AI sound effects generation, and a complete multi-speaker podcast creation studio. The update adds a web-based studio, a streaming API with sub-200ms latency, on-premises deployment for enterprises, and support for 45+ languages with native accents.

Key Takeaways

ElevenLabs Expands Generative Audio Platform with Voice Isolation, Sound Effects, and Multi-Speaker Podcast Generation — AI news article illustration

ElevenLabs has expanded its generative audio platform with significant new capabilities spanning voice isolation, sound effects, and full podcast production.

New Features

Platform Upgrades

ElevenLabs introduces a web-based studio for editing speech, adjusting pacing, and mixing multiple audio tracks. The API now supports streaming with sub-200ms latency.

Enterprise

New on-premises deployment option for enterprises with data residency requirements.

Pricing

Free tier available. Creator at $25/month. Pro at $99/month.

Frequently Asked Questions

What new features did ElevenLabs release?

Voice isolation, a sound effects generator, a multi-speaker podcast studio, and emotion-adaptive speech.

How many languages does ElevenLabs support?

More than 45 languages with native accents.

Is there an enterprise option?

Yes, a new on-premises deployment option for companies with data residency requirements.

What does pricing look like?

There is a free tier, Creator at $25 per month, and Pro at $99 per month.

This article is based on the official announcement from elevenlabs.io . Read the original for full technical details.

Related Articles

Back to all news