ElevenLabs releases v4 and v4 Turbo speech models with 90+ language support and 10-second voice cloning

ElevenLabs launched v4 and v4 Turbo models supporting 90+ languages (up from 70), voice cloning from 10 seconds of audio, and stackable inline expression tags for controlling emotion, pacing and tone. Cross-language cloning preserves speaker identity while adopting native accents.