- Organizations
- Cartesia
- Sonic 3.6
Sonic 3.6: Benchmarks, Pricing & Examples
Sonic 3.6 is a text-to-speech model from Cartesia, released in August 2026, with a 3K-token context window, and pricing from $10.00 per 1M input tokens.
Cartesia Sonic-3.6 TTS (GA 2026-08-27). 44 languages / 61 locales (new Odia or, Urdu ur; Hinglish; optional locale). Streaming, WebSocket, bytes, and SSE. Vendor latency under 90ms TTFA at ~132 chars/sec. Blind prefs up to 93% across 15
Sonic 3.6 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Quality Tracker
Sonic 3.6 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
Sonic 3.6 pricing
Providers
Sonic 3.6 starts at $10.00 per million input tokens via Cartesia.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
| $10.00 | — | — | 2.5K/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Sonic 3.6 context window
Input and output token limits for Sonic 3.6, plus how it ranks on long-context understanding.
Try now
Give your ideas
a voice.
Bring your next story, script, or creative project into your Huggle workspace.
Opens in Huggle
Sonic 3.6 latency
Sonic 3.6 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Sonic 3.6 license
Sonic 3.6 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
FAQ
Common questions about Sonic 3.6.