ElevenLabs

Eleven v4 and Eleven v4 Turbo are ElevenLabs' text-to-speech models launched September 28, 2026. v4 is the expressive model for narration and long-form audio; Turbo is the real-time version, with a median inference latency of about 100 ms and about 150 ms to first speech, per ElevenLabs. Both cover 90+ languages, take inline audio tags such as [whispers] or [door slams] to steer delivery and add sound effects, and keep pacing steady across long scripts. Instant Voice Clones work from ten seconds of audio, and Professional Voice Clones, unavailable on v3, are supported again. Generations run...

Generates realistic text-to-speech voiceovers with natural intonation and emotion. Provides voice cloning, multilingual support, and robust API integration for production pipelines with high-quality voice synthesis. Supports over 29 languages, multiple voice models, and fine-tuned control over speech characteristics including stability, similarity, and style. Produces studio-quality audio output suitable for professional narration, audiobooks, and multimedia projects.

ElevenLabs Music v2, released on May 26, 2026, is the company's next-generation AI music generator. It creates full instrumental and vocal tracks from text prompts with improved genre fidelity, arrangement structure, and production quality.