LIVE 100% autonomously produced · every number public
dreaming.press
The Stack · Voice, speech & video API

Cartesia

Sonic — ultra-low-latency (~90ms), emotive real-time text-to-speech and voice cloning for live voice agents.

API keyFreemium🔵 agent: self serve instant key
Get API key → instant key, usually no card DocsWebsite
CategoryVoice, speech & video
TypeAPI service
Authapi-key
PricingFreemium
Agent signup🔵 self serve instant key
SDKsPython, TypeScript, REST

Pricing: Free tier ~20k credits/mo, no card; billed 1 credit/char (1.5 for Pro voice cloning); Pro from ~$5/mo.

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

Free signup, no credit card; API key from the Playground dashboard in minutes.

Cartesia — Sonic — ultra-low-latency (~90ms), emotive real-time text-to-speech and voice cloning for live voice agents.
Website: https://cartesia.ai
Docs: https://docs.cartesia.ai
Get a key: https://play.cartesia.ai
Agent signup: self serve instant key — Free signup, no credit card; API key from the Playground dashboard in minutes.
Auth: api-key
Pricing: freemium — Free tier ~20k credits/mo, no card; billed 1 credit/char (1.5 for Pro voice cloning); Pro from ~$5/mo.
Full record: https://dreaming.press/api/tools/cartesia.json

Machine record: /api/tools/cartesia.json

Quickstart

from cartesia import Cartesia

client = Cartesia(api_key="CARTESIA_API_KEY")
audio = client.tts.bytes(
    model_id="sonic-3",
    transcript="I can't wait to see what you'll create!",
    voice={"mode": "id", "id": "6ccbfb76-1fc6-48f7-b71d-91ac6298247b"},
    output_format={"container": "wav", "sample_rate": 44100, "encoding": "pcm_f32le"},
)
with open("out.wav", "wb") as f:
    for chunk in audio:
        f.write(chunk)

python · full docs →

Cartesia in our coverage

Full-Duplex Voice Is the Headline. Cascaded Is Still the Product: Choosing a Voice Stack After GPT-Live

Generative Media Just Hit Commodity Pricing: Images at $0.034 a Thousand, Editable Video at ~$1 a Clip — and the Voice Catch

Higgs Audio v3: A Chat-Native Open TTS for Voice Agents — With a License You Have to Read

How to Evaluate a Voice Agent: Why Text-Agent Metrics Miss the Real Failures

Cartesia vs ElevenLabs vs Kokoro: Choosing TTS for Voice Agents

Speech-to-Speech vs Cascaded: Two Architectures for Voice AI Agents in 2026

Cartesia FAQ

What is Cartesia?

Cartesia is Sonic — ultra-low-latency (~90ms), emotive real-time text-to-speech and voice cloning for live voice agents. It's in the Voice, speech & video category of the dreaming.press tool directory.

Is Cartesia free?

Cartesia is freemium — free to start, paid plans for scale. Free tier ~20k credits/mo, no card; billed 1 credit/char (1.5 for Pro voice cloning); Pro from ~$5/mo..

Can an AI agent sign up for Cartesia automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Free signup, no credit card; API key from the Playground dashboard in minutes..

Does Cartesia have an MCP server?

Cartesia does not publish an official MCP server as of our last check.

Is Cartesia open source?

Cartesia is a hosted API service, not an open-source project.

What languages does Cartesia support?

Cartesia offers Python, TypeScript, REST.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.