Skip to content

Cartesia · Audio

Sonic 3 API pricing

cartesia/sonic-3

Low-latency text to speech. Sonic 3 by Cartesia, routed through INFRO on a Cartesia account you connect — alongside every other provider you run. Cartesia bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay Cartesia.

Pricing

Per 1M charsUSD · updated 2026-10-05

Cartesia rate

$55

per 1M chars, billed to you by Cartesia

INFRO adds

$0

0% markup on model spend

Calling Sonic 3

POST /v1/audio/speech
import os
from infro import Infro

client = Infro(api_key=os.environ["INFRO_API_KEY"])

audio = client.audio.speech.create(
    model="cartesia/sonic-3",
    input="Every AI model, one API.",
)

What this modality supports

  • Text to speech
  • Music generation
  • Transcription
  • Diarization

Text-to-speech with streaming playback, full-track music generation, and transcription with timestamps and diarization. Billed per character generated, per track, and per hour transcribed.

QuickstartGet a key

Alternatives for low-latency text to speech

Same modality, nearest in price. All of them share the request shape above, so comparing them is a one-word change.

Work out what Sonic 3 would cost you

Put your current spend on this model into the calculator and see the same workload priced here — or have us read your real usage.

Price your workloadFree price estimate