Cartesia Ink (ink-2, ink-whisper)

Overview

Best for: Voice agents already using Cartesia Sonic TTS who want one credit pool and turn-aware STT.

At a glance

Credit-based. $0.39/hr is ink-2 on the Scale plan (vendor); ink-2 on Pro overage is about $0.70/hr; ink-whisper about $0.13/hr on Scale. Concurrency 12 is the Pro plan (Free 8, Scale 60). Free plan 20K credits/month shared with TTS. BAA on Enterprise plans only. Turn detection via the /stt/turns endpoint.

Features

• interim and final transcripts (is_final)
• finalize command to flush
• word timestamps
• keyterms (ink-2)
• turn-based endpoint /stt/turns/websocket
• access tokens for browsers

Pricing

Free tier: Free plan: 20K credits/month (about 1h51m of ink-2 per plan table).

Source: docs.cartesia.ai

Setup

1. Create an API key at play.cartesia.ai.
2. Connect to wss://api.cartesia.ai/stt/websocket?model=ink-2&encoding=pcm_s16le&sample_rate=16000&cartesia_version=2026-08-14 with header X-API-Key.
3. Send binary audio; send text 'finalize' to flush, 'close' to end.
4. Browsers: mint a short-lived access token server-side and pass access_token= in the URL.

Endpoint

wss://api.cartesia.ai/stt/websocket (turn-based: /stt/turns/websocket)

Authentication

X-API-Key header server-side; access_token query param for clients.

import asyncio, json, os, websockets  # pip install websockets>=14

URL = ("wss://api.cartesia.ai/stt/websocket?model=ink-2&encoding=pcm_s16le"
       "&sample_rate=16000&cartesia_version=2026-08-14")

async def main():
    hdr = {"X-API-Key": os.environ["CARTESIA_API_KEY"]}
    async with websockets.connect(URL, additional_headers=hdr) as ws:
        async def send():
            with open("audio_16k_mono.raw", "rb") as f:
                while chunk := f.read(3200):  # 100 ms
                    await ws.send(chunk)
                    await asyncio.sleep(0.1)
            await ws.send("finalize")
            await ws.send("close")
        asyncio.create_task(send())
        final = ""
        async for msg in ws:
            d = json.loads(msg)
            if d["type"] == "transcript":
                if d["is_final"]:
                    final += d["text"]  # deltas: do not strip or add spaces
                print("FINAL" if d["is_final"] else "partial", d["text"])
            elif d["type"] in ("done", "error"):
                print(final or d); break

asyncio.run(main())

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 12 warnings that apply to all speech-to-text, live APIs. See category warnings.

Limits

• STT concurrent requests: Free 8, Pro 12, Startup 20, Scale 60, Enterprise custom (separate pool from TTS).
• With overages disabled, requests fail when credits run out.

Models and products

Docs and sources

Docs

• STT WebSocket reference
• Pricing docs
• Plans

Sources used

• docs.cartesia.ai/api-reference/stt/stt
• docs.cartesia.ai/pricing.md
• cartesia.ai/pricing
• cartesia.ai/ink