ElevenLabs

ElevenLabs Scribe v2

Name: ElevenLabs Scribe v2
Price: 0.016 USD
Availability: InStock
Rating: 92.5 (2 reviews)
Author: ElevenLabs

ElevenLabs’ second-generation speech-to-text — 90+ languages, speaker diarization and sub-200ms streaming.

#10发布于 2026年10月19日·Proprietary·Not disclosed

audio64K ctx

API 提供商运行模型 →对比 Cartesia Ink Whisper 排行榜

智商指数

92.5 #10

AAQI 93.0

输出速度

240 t/s

ITL 4.2 ms/tok

混合价格 (3:1)

$0.01 /1M

输入 $0.008/M · 输出 $0.016/M

上下文

64K

≈ 160 页 A4 · 最大输出 8,192

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

ElevenLabs Scribe v2

Claude Mythos Preview (#1)

Average (68)

缺少直接基准测量时，雷达图各轴由类别得分近似得出 — 详见评分方法。

优势与取舍

优势所在

Top-tier WER across 90+ languages
Realtime partials fast enough for barge-in agents
Built-in diarization — no extra pipeline

需要注意的权衡

STT only — pair with an LLM and TTS for full loops
Per-minute pricing adds up on call centers
No on-prem option

杀手级用例

Voice-agent front end

Streaming transcripts with low-latency turn detection.

Meeting intelligence

Diarized, timestamped records at scale.

Multimedia subtitling

Multi-language caption pipelines.

开发者快速上手与 API

请先设置 ELEVENLABS_API_KEY — 获取 API 密钥

curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID" \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Welcome to the future of voice agents.", "model_id": "scribe_v2"}' \
  --output speech.mp3

import os, requests

resp = requests.post(
    "https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID",
    headers={"xi-api-key": os.environ["ELEVENLABS_API_KEY"]},
    json={"text": "Welcome to the future of voice agents.", "model_id": "scribe_v2"},
)
open("speech.mp3", "wb").write(resp.content)

const res = await fetch("https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID", {
  method: "POST",
  headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({ text: "Welcome to the future of voice agents.", model_id: "scribe_v2" }),
});
await fs.promises.writeFile("speech.mp3", Buffer.from(await res.arrayBuffer()));

Text-to-speech — replace VOICE_ID with a voice from your library; returns an audio stream.

官方资源与链接

发布公告Scribe v2 文档API docs API 控制台ElevenLabs app

API 部署

对比托管商与延迟

Groq、Cerebras、Together、DeepInfra、Fireworks、Bedrock 与 Azure 的吞吐量、TTFT 和缓存定价。

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI

查看提供商矩阵 →

各榜单得分

Arena.ai ↗

1460.0

#11 · 2.6k votes · ±6

Artificial Analysis ↗

分类能力得分

速度98.0 Intelligence92.5 多模态90.0 性价比85.0 智能体70.0 知识50.0 长上下文50.0 推理30.0 编程0.0 数学0.0

基准测试分项

实时对决

vsCartesia Ink Whisper+0.7 vsEleven Multilingual v3-1.5 vsClaude Fable 5-0.9 vsGPT-Image 2-0.6 vsGrok Imagine Quality-0.1 所有对比 →

实时规格与架构

底层解析

Scribe v2 — streaming speech recognition

90+ languages with automatic language ID
Speaker diarization and word-level timestamps
Sub-200ms partial transcripts for live agents
Noise-robust far-field microphone handling

发布日期

2026年10月19日

架构

Scribe v2 — streaming speech recognition

参数量

Not disclosed

开源协议

Proprietary

上下文窗口

64,000 tokens

最大输出

8,192 tokens

模态

audio

缓存价格

读 $0.003 · 写 $0.01 /1M

推理

—

输入价格

$0.008/M

输出价格

$0.016/M

输出速度

240 t/s

首Token延迟

—

数据更新

2026年10月22日

每月账单预估

每月 API 请求数: 100,000平均输入 token 数: 1,500平均输出 token 数: 500提示缓存命中率: 50%

每月预估支出

$0.00

正在计算相对 GPT-4o 的节省额…

引用与嵌入

GitHub Markdown 徽章

Loading badge markdown...

BibTeX

@misc{llmpodium2026elevenlabsscribev2,
  title = {Benchmark Analysis and Intelligence Evaluation of ElevenLabs Scribe v2},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/elevenlabs-scribe-v2}
}