Cartesia

Cartesia STT (ink-whisper) and TTS (sonic) providers.

Cartesia STT

Streaming speech-to-text using Cartesia’s ink-whisper model. Pure-aiohttp transport, no vendor SDK required.

Install

pip install "getpatter[cartesia]"

Usage

# Namespaced import
from getpatter.stt import cartesia

stt = cartesia.STT()                                      # reads CARTESIA_API_KEY
stt = cartesia.STT(api_key="csk_...", language="en")

# Flat alias (equivalent)
from getpatter import CartesiaSTT

stt = CartesiaSTT()

Plug it into an agent:

import asyncio
from getpatter import Patter, Twilio, CartesiaSTT, ElevenLabsTTS

phone = Patter(carrier=Twilio(), phone_number="[phone]")

agent = phone.agent(
    stt=CartesiaSTT(),                                    # CARTESIA_API_KEY from env
    tts=ElevenLabsTTS(voice_id="rachel"),
    system_prompt="You are a helpful assistant.",
)

asyncio.run(phone.serve(agent))

Supported sample rates: 8000, 16000, 24000, 44100, 48000 Hz.

Low-level usage

from getpatter.providers.cartesia_stt import CartesiaSTT as _LowLevelSTT

stt = _LowLevelSTT(api_key="csk_...", language="en")
await stt.connect()
await stt.send_audio(pcm_chunk)  # 16 kHz PCM s16le
async for t in stt.receive_transcripts():
    print(t.text, t.is_final, t.confidence)
await stt.close()

Cartesia TTS

CartesiaTTS is a Patter TTSProvider backed by Cartesia’s bytes endpoint. It streams raw PCM_S16LE chunks that drop directly into Patter’s pipeline with no transcoding.

Usage

# Namespaced import
from getpatter.tts import cartesia

tts = cartesia.TTS()                                      # reads CARTESIA_API_KEY
tts = cartesia.TTS(voice="f786b574-daa5-4673-aa0c-cbe3e8534c02")  # Katie

# Flat alias (equivalent)
from getpatter import CartesiaTTS

tts = CartesiaTTS(voice="f786b574-daa5-4673-aa0c-cbe3e8534c02")

In an agent:

from getpatter import Patter, Twilio, DeepgramSTT, CartesiaTTS

phone = Patter(carrier=Twilio(), phone_number="[phone]")

agent = phone.agent(
    stt=DeepgramSTT(),
    tts=CartesiaTTS(voice="f786b574-daa5-4673-aa0c-cbe3e8534c02"),
    system_prompt="You are a helpful assistant.",
)

Options

Option	Default	Notes
api_key	None	Reads from CARTESIA_API_KEY when omitted.
model	"sonic-2"	Any Cartesia TTS model id (e.g. "sonic-3").
voice	"f786b574-..."	Cartesia voice id.
language	"en"	ISO 639-1 code.
sample_rate	16000	Hz.
speed	None	"fastest" ... "slowest" or float in [0.6, 2.0].
emotion	None	See Cartesia’s emotion list.
volume	None	Float in [0.5, 2.0] for sonic-3.