ElevenLabs releases Eleven v4 voice model
What happened
On September 29, 2026, The Decoder reported that ElevenLabs released the Eleven v4 voice model. The report says the model follows emotion, pause and sound-effect tags in a script more accurately, and keeps the same voice across long productions. A new architecture also drives a Turbo version for real-time voice agents; in official tests Turbo starts speaking in about 150 milliseconds, against 262 milliseconds for Cartesia Sonic 3.6 and 814 milliseconds for OpenAI GPT-4o mini TTS.
Written by AI from the coverage · updated 7 hours ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderElevenLabs' new v4 speech model makes AI voices more expressive and consistent
ElevenLabs 发布 Eleven v4 语音模型，能更准确跟随脚本中的情绪、停顿与音效标签，并在长篇制作中保持音色一致。新架构同时驱动 Turbo 版本，官方测试中约 150 毫秒开始输出语音，对比 Cartesia Sonic 3.6 的 262 毫秒和 OpenAI GPT-4o mini TTS 的 814 毫秒。
Heat over time
Heat now 7·Comparable peak 8（Sep 30 06:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.