ElevenLabs · 文本转语音

Eleven v4

Eleven v4 is ElevenLabs' most expressive speech model, suited to narration, audiobook excerpts, advertising voiceovers and character lines where emotional delivery matters. It follows inline audio tags in brackets, such as [whispers] or [laughs], to shape a performance, and speaks more than 90 languages fluently. Flowctory generates an MP3 with one selected voice and a stability choice: lower is more expressive, higher is more consistent between takes. Review pronunciation and tone before publishing.