Cartesia

Cartesia Ink Whisper

Cartesia’s streaming speech-recognition model — 90ms time-to-first-token for real-time voice agents.

#12dirilis 6 Okt 2026·Proprietary·Not disclosed
audio64K ctx
Inteligensi
91.8 #12
AAQI 92.0
Kecepatan output
260 t/s
ITL 3.8 ms/tok
Harga gabungan (3:1)
$0.008 /1M
Input $0.006/M · Output $0.012/M
Konteks
64K
≈ 160 halaman A4 · output maks 8,192

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Cartesia Ink Whisper
Claude Mythos Preview (#1)
Average (68)
Coding (15)Mathematics (15)Hard Science (GPQA) (28)Agentic & Tool Use (68)Knowledge (MMLU) (45)Vision / Multimodal (88)

Sumbu radar diaproksimasi dari skor kategori jika pengukuran benchmark langsung tidak tersedia — lihat Metodologi.

Kelebihan & Trade-off

Di mana ia menang

  • Fastest streaming STT — 90ms TTFT
  • 260× realtime-factor transcription
  • Cheapest per-minute tier among premium STT

Hal yang perlu diperhatikan

  • Accuracy dips on heavy accents vs. Scribe
  • Smaller language coverage than ElevenLabs
  • STT only

Kasus Penggunaan Killer

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.

Quickstart Developer & API

Atur CARTESIA_API_KEY dulu — dapatkan kunci API
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."}]
  }'

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
Lihat matriks penyedia →

Skor per sumber

Duel Head-to-head Live

Spesifikasi Live & Arsitektur

Di balik kap
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
Tanggal rilis
6 Okt 2026
Arsitektur
Ink Whisper — state-space streaming STT
Parameter
Not disclosed
Lisensi
Proprietary
Jendela konteks
64,000 tokens
Output maks
8,192 tokens
Modalitas
audio
Harga cache
baca $0.002 · tulis $0.008 /1M
Penalaran
—
Harga input
$0.006/M
Harga output
$0.012/M
Kecepatan output
260 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{llmpodium2026cartesiainkwhisper,
  title = {Benchmark Analysis and Intelligence Evaluation of Cartesia Ink Whisper},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/cartesia-ink-whisper}
}

Sematkan Lencana Skor

Tambahkan lencana Podium Score langsung ke README GitHub atau Hugging Face Anda — menautkan ke peringkat langsung.

Pratinjau
Cartesia Ink Whisper LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Model Alternatif

Alternatif terdekat untuk Cartesia Ink Whisper berdasarkan kemampuan, harga, dan skor benchmark.

0 / 4