概念

text-to-speech

Q: 什么是 text-to-speech？

将文本转换为语音的生成模型与技术。

Q: text-to-speech 最近有什么新动态？

traeai 已收录 2 篇与 text-to-speech 相关的内容。最新一篇是「Another banger open-source release. Miso One is an 8B text-to-speech model with real emotional ran...」，由 elvis(@omarsar0) 发布。

别名：TTS

将文本转换为语音的生成模型与技术。

已跟踪 2 条高相关材料

TraeAI 观察

如果只读 3 篇

Another banger open-source release. Miso One is an 8B text-to-speech model with real emotional ran...

elvis(@omarsar0) · 7.8 分

Miso One 是开源 8B 参数情感 TTS 模型，支持温暖、犹豫、兴奋等真实情感，110ms 低延迟，适合短视频、播客与教育内容，权重全开源可自宿与微调。

At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech - a new model architecture...

ElevenLabs(@elevenlabsio) · 7.5 分

ElevenLabs 在华沙峰会上展示了其在设备端文本转语音（TTS）领域的最新进展，推出了一种新型模型架构，可在无互联网连接的情况下，在有限硬件上实现接近人类水平的语音质量。

Miso One Emotional Open-Source TTS Model Released

elvis(@omarsar0)6月4日208 字 (约 1 分钟)

Miso One is an open-source 8B-parameter emotional text-to-speech model that generates speech with warmth, hesitation, and excitement, achieving 110ms latency for real-time voiceover tasks. It is purpose-built for shorts, podcasts, and educational content, with fully open weights enabling self-hosting, fine-tuning, and data privacy protection.

入选理由：Miso One 为 8B 参数情感 TTS 模型，支持温暖、犹豫、兴奋等真实情感表达。

FeaturedTweet#TTS#Open Source#Voiceover#Miso One#8B Parameters英文

At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech - a new model architecture...

ElevenLabs Unveils On-device Text-to-Speech at Warsaw Summit

ElevenLabs(@elevenlabsio)6月2日105 字 (约 1 分钟)

At the ElevenLabs Summit in Warsaw, the company previewed a new model architecture for on-device Text-to-Speech (TTS) that delivers human-level quality on limited hardware without requiring an internet connection.

入选理由：新型模型架构支持在设备端运行，无需互联网连接。

FeaturedTweet#ElevenLabs#Text-to-Speech#On-device#AI#Speech Synthesis英文

跨材料问答 · text-to-speech

回答基于：text-to-speech 相关 2 条材料