Creators and developers can generate performed dialogue or build low-latency voice agents through ElevenLabs products and APIs. Core capabilities include Expressive text-to-speech, Multi-speaker dialogue, Inline emotion tags, and Audio-event direction.
Use the provider's product or developer platform; account access and the available usage plan determine deployment options. Additional characteristics include Pause and emphasis control, Pronunciation dictionaries, Streaming and non-streaming APIs, and A low-latency Turbo variant.
