Cartesia
Cartesia Ink Whisper
Cartesia’s streaming speech-recognition model — 90ms time-to-first-token for real-time voice agents.
智商指数
91.8 #12
AAQI 92.0
输出速度
260 t/s
ITL 3.8 ms/tok
混合价格 (3:1)
$0.008 /1M
输入 $0.006/M · 输出 $0.012/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
Cartesia Ink Whisper
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
- Fastest streaming STT — 90ms TTFT
- 260× realtime-factor transcription
- Cheapest per-minute tier among premium STT
需要注意的权衡
- Accuracy dips on heavy accents vs. Scribe
- Smaller language coverage than ElevenLabs
- STT only
杀手级用例
Barge-in voice agents
Instant partials let agents interrupt naturally.
Live captioning
Sub-second captions for calls and streams.
Telephony analytics
Realtime intent extraction on 8kHz audio.
开发者快速上手与 API
请先设置
CARTESIA_API_KEY — 获取 API 密钥curl https://api.cartesia.ai/v1/chat/completions \
-H "Authorization: Bearer $CARTESIA_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "ink-whisper",
"messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.cartesia.ai/v1",
api_key=os.environ["CARTESIA_API_KEY"],
)
resp = client.chat.completions.create(
model="ink-whisper",
messages=[{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}],
)
print(resp.choices[0].message.content)const res = await fetch("https://api.cartesia.ai/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.CARTESIA_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
model: "ink-whisper",
messages: [{ role: "user", content: "Refactor this function for O(n) time and explain the change." }],
}),
});
console.log((await res.json()).choices[0].message.content);官方资源与链接
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
各榜单得分
分类能力得分
基准测试分项
实时对决
实时规格与架构
底层解析
Ink Whisper — state-space streaming STT
- State-space architecture — linear-time streaming decode
- 90ms time-to-first-transcript-token
- Endpointing tuned for conversational turn-taking
- On-device-friendly distilled variants
发布日期
2026年10月6日
架构
Ink Whisper — state-space streaming STT
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 $0.002 · 写 $0.008 /1M
推理
—
输入价格
$0.006/M
输出价格
$0.012/M
输出速度
260 t/s
首Token延迟
—
数据更新
2026年10月22日
每月账单预估
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{llmpodium2026cartesiainkwhisper,
title = {Benchmark Analysis and Intelligence Evaluation of Cartesia Ink Whisper},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/cartesia-ink-whisper}
}嵌入评分徽章
将实时 Podium 评分徽章添加到 GitHub 或 Hugging Face README —— 链接回实时排名。
预览
Markdown
Loading badge snippet...HTML
Loading badge snippet...替代模型推荐
基于能力、定价和基准测试得分与 Cartesia Ink Whisper 最接近的替代模型。