StepFun
Step Audio 2
StepFun’s end-to-end speech model — TTS, STT and voice chat in a single checkpoint.
Inteligensi
89.0 #22
AAQI 89.0
Kecepatan output
150 t/s
ITL 6.7 ms/tok
Harga gabungan (3:1)
$0.015 /1M
Input $0.012/M · Output $0.024/M
Konteks
64K
≈ 160 halaman A4 · output maks 8,192
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Step Audio 2
Claude Mythos Preview (#1)
Average (68)
Sumbu radar diaproksimasi dari skor kategori jika pengukuran benchmark langsung tidak tersedia — lihat Metodologi.
Kelebihan & Trade-off
Di mana ia menang
- Single model replaces a whole voice pipeline
- Best-in-class Chinese speech quality
- Understands tone and emotion, not just words
Hal yang perlu diperhatikan
- English prosody below Eleven/Cartesia tiers
- Ecosystem concentrated in APAC
- No self-hosting
Kasus Penggunaan Killer
Speech-to-speech agents
Direct voice chat without TTS/STT glue.
Chinese voice products
Native Mandarin/Cantonese synthesis and ASR.
Emotion-aware bots
Reacts to caller sentiment in real time.
Quickstart Developer & API
Atur
STEPFUN_API_KEY dulu — dapatkan kunci APIcurl https://api.stepfun.com/v1/chat/completions \
-H "Authorization: Bearer $STEPFUN_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "step-audio-2",
"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.stepfun.com/v1",
api_key=os.environ["STEPFUN_API_KEY"],
)
resp = client.chat.completions.create(
model="step-audio-2",
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.stepfun.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.STEPFUN_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
model: "step-audio-2",
messages: [{ role: "user", content: "Refactor this function for O(n) time and explain the change." }],
}),
});
console.log((await res.json()).choices[0].message.content);Sumber Daya & Tautan Resmi
Deployment API
Bandingkan host & latensi
Throughput, TTFT, dan harga cache di Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock, dan Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Skor per sumber
Skor per kategori
Hasil benchmark
Spesifikasi Live & Arsitektur
Di balik kap
Step Audio 2 — unified speech model
- One checkpoint for TTS, STT and speech-to-speech chat
- Paralinguistic understanding — emotion, emphasis, age cues
- Voice-to-voice tool calling for agent stacks
- Strong Mandarin/Cantonese coverage
Tanggal rilis
24 Sep 2026
Arsitektur
Step Audio 2 — unified speech model
Parameter
Not disclosed
Lisensi
Proprietary
Jendela konteks
64,000 tokens
Output maks
8,192 tokens
Modalitas
text + audio
Harga cache
baca $0.004 · tulis $0.015 /1M
Penalaran
—
Harga input
$0.012/M
Harga output
$0.024/M
Kecepatan output
150 t/s
Waktu ke token pertama
—
Data diperbarui
22 Okt 2026
Estimasi tagihan bulanan
Estimasi pengeluaran bulanan
$0.00
Menghitung penghematan vs GPT-4o…
Kutip & sematkan
Badge Markdown GitHub
Loading badge markdown...BibTeX
@misc{llmpodium2026stepaudio2,
title = {Benchmark Analysis and Intelligence Evaluation of Step Audio 2},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/step-audio-2}
}Sematkan Lencana Skor
Tambahkan lencana Podium Score langsung ke README GitHub atau Hugging Face Anda — menautkan ke peringkat langsung.
Pratinjau
Markdown
Loading badge snippet...HTML
Loading badge snippet...Lainnya dari StepFun
Model Alternatif
Alternatif terdekat untuk Step Audio 2 berdasarkan kemampuan, harga, dan skor benchmark.