Cartesia Ships Sonic-3.6: Streaming TTS Now Leads Both Speech Arenas

On August 17, 2026, Cartesia released Sonic-3.6 in beta — just three months after Sonic-3.5. The headline claim is verifiable: Sonic-3.6 now sits at #1 on both Artificial Analysis speech leaderboards. 1,283 Elo on the Provider Voice board and 1,123 on the Controlled Voice board. The second number matters more. That board clones every model onto the same eight reference voices, isolating the synthesis engine from the voice catalog. If you top that ranking, the model itself got better — not just the voice library.

Cartesia is not open-sourcing anything. Sonic-3.6 is a hosted API, available on sonic-preview. No weights, no Hugging Face repo. You rent it. Full details on Cartesia's Sonic page.

What Changed From 3.5

The version gap is only three months, but the improvements land in specific places:

• Naturalness across languages. Cartesia describes a "step change in naturalness across 44 languages," with new support for Odia and Urdu.
• Locale codes. Pass en-GB instead of en and 05/04/2026 reads as "the fifth of April" instead of "May fourth." Previously you had to work around this with spelled-out dates.
• English heteronyms. Words like "read," "bass," and "bow" now resolve correctly in context without spell tags.
• Backwards compatible. Sonic-3.6 is a drop-in replacement for Sonic-3.5 — same voice IDs, same request shape, no code changes required.

The architecture remains state space models, not transformers. Cartesia frames this as the reason for the latency advantage: sub-90ms time-to-first-audio on their benchmark, compared to transformer-based TTS systems that typically land in the 200–400ms range.

What the Leaderboard Actually Measures

Artificial Analysis runs two separate TTS leaderboards. Understanding the difference matters if you're evaluating providers:

Provider Voice tests each model with the vendor's own best voices. This measures the total experience — synthesis quality plus voice catalog. Sonic-3.6 leads here with 1,283 Elo, ahead of Sonic-3.5 and ElevenLabs Eleven v3.

Controlled Voice is the apples-to-apples comparison. Every model runs on the same eight reference voices, so voice quality is constant. The only variable is the synthesis engine. Sonic-3.6 leads this board too at 1,123 Elo, with Sonic-3.5 second and ElevenLabs third.

That second result is the one that should worry competitors. It means Cartesia's synthesis engine — the part that turns text into audio waveforms — genuinely improved. Not "we added better voices."

Getting Started

The API surface is straightforward. Here's a minimal TypeScript example:

import { CartesiaClient } from "@cartesia/cartesia-js";

const client = new CartesiaClient({
  apiKey: process.env.CARTESIA_API_KEY,
});

const audio = await client.tts.bytes({
  modelId: "sonic-preview",
  transcript: "Hello from Sonic 3.6. This is streaming text-to-speech.",
  voice: {
    mode: "id",
    id: "820a4f59-ad9b-449c-a45b-480eeadb6773",
  },
  language: "en",
  outputFormat: { container: "raw", encoding: "pcm_f32le", sampleRate: 24000 },
});

// Stream the audio chunks
for await (const chunk of audio) {
  process.stdout.write(chunk);
}

Switching from 3.5? Change the modelId to sonic-preview and keep everything else identical. The changelog confirms full backwards compatibility with existing voice IDs and request schemas.

For inline expressions, drop tags directly into the transcript:

const transcript = `
That's hilarious! [laughter]
But seriously, the order number is 
<spell>A-T-7-2-9-1-4</spell> and your 
confirmation code is <spell>B-X-0-3</spell>.
`;

Cartesia's prompting guide notes that <spell> tags still work the same way — you just get better-sounding output now.

The Pricing Question

At $49 per million characters, Sonic-3.6 sits in a specific tier. Half the price of ElevenLabs Eleven v3 at $100/M, but well above Speechify Simba 3.2 at $10/M (which scores 1,240 Elo on the Provider Voice board — roughly 43 points behind).

For production workloads, Cartesia sells credits through tiers. The Pro plan starts at $5/month. Scale at $299/month includes roughly 10,667 TTS minutes and 15 concurrent requests. Voice agents through their Line product bill separately at $0.06 per minute.

The real cost comparison depends on your use case. For high-volume contact centers, the latency advantage translates directly to shorter calls and lower per-interaction cost. For content creation, the quality gap between 1,283 and 1,240 Elo may not justify a 5x price difference.

What This Means for Voice Agent Builders

If you're building voice agents, Sonic-3.6's Controlled Voice leadership is the number to watch. That leaderboard isolates synthesis quality from voice selection, which means the engine itself handles agent transcripts better — confirmation codes, heteronyms, inline expressions — without preprocessing.

Cartesia's Line product already bundles Sonic TTS with Ink-2 STT (speech-to-text). The combined pipeline runs at sub-90ms TTS latency and 100ms STT latency, both vendor-stated. For real-time voice agents where every millisecond of round-trip time matters, that stack is competitive.

The catch: Sonic-3.6 is beta. Cartesia's docs still list Sonic 3.5 as the stable, production-ready model. The sonic-preview model ID can change without notice, and there are no SLAs on performance. If you're shipping to production today, pin to sonic-3.5. If you're evaluating for a future deployment, Sonic-3.6 is worth testing now.

Related

• Needle 2: A 14MB Model That Calls Tools on Any Device — Edge-native tool calling that runs entirely offline.
• When AI Agents Start a Turf War — What happens when multiple Claude agents fight over the same codebase.