Ink-Whisper: Pricing, Performance & Examples
Ink-Whisper is a speech-to-text model from Cartesia, released in December 2024, with pricing from $2.60 per 1M input tokens.
Cartesia Ink-Whisper STT model with streaming and batch support
Ink-Whisper pricing
Providers
Ink-Whisper starts at $2.60 per million input tokens via Cartesia.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Cartesia | $2.60 | — | — | —/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Ink-Whisper API
Any audio format up to 25 MB.
Run a request to see the response
Use it in your code
OpenAI-compatible endpoint through the LLM Stats gateway.
import requests
with open("audio.mp3", "rb") as f:
response = requests.post(
"https://gateway.llm-stats.com/v1/stt/transcribe",
headers={"Authorization": "Bearer YOUR_API_KEY"},
files={"file": f},
data={"model_id": "ink-whisper"},
)
print(response.json()["text"])Need an API key? Create one above in the playground, or read the API documentation.
Ink-Whisper latency
Ink-Whisper time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Ink-Whisper license
Ink-Whisper is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
FAQ
Common questions about Ink-Whisper.