ElevenLabs

About This Agent
From transcribing a caller to generating a spoken reply, ElevenLabs provides multilingual speech models and APIs for building voice agents.
Official websiteAgent Capabilities
- Multilingual speech synthesis and transcription
- Voice agent APIs
- Low-latency speech-to-text for real-time transcription and agent interaction
- Multilingual dubbing that clones original speaker voice across 30+ languages
Primary Workflows & Use Cases
- Build a multilingual voice agent from transcription and speech generation APIs.
- Generating lifelike narration for a video.
- Adding speech to an application via API.
- Running a voice agent for customer calls.
Similar Synthetic Media & Creative Studio Agents
Explore alternatives and related autonomous systems in this category.
The performer's movement can stay the same while the character changes in Genjutsu AI. Motion Transfer restyles the footage from a reference image, and Object Swap targets one prop, product or character in the shot.
Wan 2.5 generates video from text or a reference image and supports editing or extending a clip. It also produces images and synchronized audio.
LMNT previously offered text-to-speech, voice cloning from short samples and streaming audio for developers. Its speech service has ended.
Keevx turns a product link, photo or script into a presenter video with lip sync. Its other tools include video translation and avatar cloning.
Are you the author of ElevenLabs? Claim your official badge.