产品精选

Artificial Analysis 推出 TTFA 基准:衡量 TTS 模型首声延迟,最快 76 ms

精选理由

做语音智能体的朋友看这个。Artificial Analysis 新出了 TTFA 基准,专门测 TTS 首声延迟:Simba 3.5 只要 116 ms,Eleven v4 开 Turbo 后从 653 ms 降到 258 ms,非流式模型中位数却要 2 秒。选 TTS 供应商前先看这张榜单,延迟直接决定对话体验。

Artificial Analysis 发布 Time to First Audio(TTFA)基准,专门测量 Text to Speech 模型从请求到用户实际听到声音的延迟。测试每天在相同的 12 条提示、四种输入长度上运行,计时的是可听语音而非首个字节,并报告 7 天滚动均值。目前领先模型的等待时间从 76 ms 到近 1 秒不等。

正文

具体成绩方面,Speechify 的 Simba 3.5 首声延迟 116 ms,是 200 ms 内起播模型中 Arena Elo 最高的;Inworld 的 Realtime TTS-2 以 186 ms 紧随其后。ElevenLabs 的 Eleven v4 Turbo 为 258 ms,而同 Elo 的 Eleven v4 需要 653 ms;Fish Audio Drama 3 同为 258 ms,Cartesia 的 Sonic 3.6 为 287 ms。

基准还揭示了一个关键分水岭:65 个支持流式输出的模型通常几百毫秒内起播,中位数 376 ms;20 个非流式模型必须完成全部生成才能返回,中位数达 2.0 秒。对于语音智能体开发者来说,流式 TTS 是实现实时对话体感的前提。

原文 · Artificial Analysis

Announcing Artificial Analysis Time to First Audio, measuring how quickly Text to Speech models start speaking. Among the leading models the wait ranges from 76 ms to nearly a second

Our Text to Speech benchmarks already cover quality, pronunciation and generation speed, but not how long a user waits before hearing anything — the number that decides whether a voice agent feels responsive. We measure every model daily on the same 12 prompts across four input lengths, timing audible speech rather than the first byte, and report a rolling 7-day mean.

Key results:

➤ Fastest at the frontier: @SpeechifyAI's Simba 3.5 starts in 116 ms — the highest Arena Elo of any model that begins speaking in under 200 ms. @InworldAI's Realtime TTS-2 follows at 186 ms.

➤ Turbo variants earn their name: @ElevenLabs' Eleven v4 Turbo starts in 258 ms against 653 ms for Eleven v4, at the same Arena Elo. @FishAudio's Fish Audio Drama 3 matches it at 258 ms and @cartesia's Sonic 3.6 is at 287 ms.

➤ Streaming is the dividing line: The 65 streaming models typically begin speaking within a few hundred milliseconds, a median of 376 ms. The 20 non-streaming models must finish generating before they return anything: a median of 2.0 seconds.

See more details below ⬇️

产业坐标与信源核验

本条情报归属 AITOP「产品」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:TTS、Artificial Analysis、ElevenLabs、Speechify,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「Artificial Analysis」(@ArtificialAnlys),经 AITOP 多维评分管线结构化提炼。