Model provider7 models

Cartesia

Cartesia serves 7 audio models on LLM API, all from Cartesia.

Models and prices

Prices when Cartesia serves the request.

Audio 7

Price per minute of audio or per 1K characters

Sort

Audio models on Cartesia and their prices on LLM API

Cartesia Sonic 3.5`sonic-3.5`	Text to speech	$0.078/ 1K characters
Cartesia Sonic 3 (2026-01-12)`sonic-3-2026-01-12`	Text to speech	$0.065/ 1K characters
Cartesia Sonic 3`sonic-3`	Text to speech	$0.065/ 1K characters
Cartesia Ink Whisper`ink-whisper`	Transcription	$0.0022/ minute
Cartesia Ink 2 (Streaming)`ink-2`	Live transcription	$0.013/ minute
Cartesia Sonic Turbo`sonic-turbo`	Text to speech	$0.045/ 1K characters
Cartesia Sonic 2`sonic-2`	Text to speech	$0.065/ 1K characters

Send requests to Cartesia

Use the model ID as it is: video, audio and embedding requests take no provider prefix.

Example: Cartesia Sonic 3.5

POST /v1/audio/speechSet LLMAPI_KEY to your LLM API key.Speech docs

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

speech = client.audio.speech.create(
    model="sonic-3.5",
    voice="f786b574-daa5-4673-aa0c-cbe3e8534c02",
    input="Hello from LLM API",
)
speech.write_to_file("hello.mp3")

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmapi.ai/v1",
  apiKey: process.env.LLMAPI_KEY,
});

const speech = await client.audio.speech.create({
  model: "sonic-3.5",
  voice: "f786b574-daa5-4673-aa0c-cbe3e8534c02",
  input: "Hello from LLM API",
});
fs.writeFileSync("hello.mp3", Buffer.from(await speech.arrayBuffer()));

curl https://api.llmapi.ai/v1/audio/speech \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonic-3.5",
    "voice": "f786b574-daa5-4673-aa0c-cbe3e8534c02",
    "input": "Hello from LLM API"
  }' \
  --fail-with-body --output hello.mp3

Prices synced October 27, 2026.