How fast is Cartesia Sonic 3.6?

Coval measures a median time to first audio of 285.8 ms and a P95 of 374.4 ms for Cartesia Sonic 3.6, over 30 days from the US East in English (Visible delay tier).

How much does Cartesia Sonic 3.6 cost?

The benchmarks print a list price of $39.20 to $50 per million characters for Cartesia Sonic 3.6.

Which languages was Cartesia Sonic 3.6 tested in?

Artificial Analysis or Speko tested Cartesia Sonic 3.6 in Arabic, Chinese, French, German, Hindi, Japanese, Portuguese, Spanish, Vietnamese.

Cartesia · Proprietary · Read 2026-10-27

Cartesia Sonic 3.6: latency, voice quality, price and languages

Rank: 14 / 23
Speed tier: Visible delay
P95: 374.4 ms
Price / 1M chars: $39.20 to $50

Cartesia Sonic 3.6 is a proprietary text-to-speech model from Cartesia. Coval measures a median of 285.8 ms and a P95 of 374.4 ms to first audio, which puts it in the Visible delay speed tier, rank 14 of 23 in the multilingual ranking. Artificial Analysis or Speko tested it in 9 languages.

This summary is generated from the measures below; it is not a vendor description. Measures a source does not hold are shown as n/a and are never estimated.

Speed (Coval, 30 days, US East, English)

Speed tier	Visible delay
Median time to first audio	285.8 ms
P90	350.6 ms
P95	374.4 ms
Mean	292.1 ms
Standard deviation	70.5 ms
Calls in the window	2,807
Cekura median, streamed text	270 ms
Cekura median, full text	286 ms

Voice quality (never added together)

Listener Elo (Artificial Analysis)	1,292 ±14
Customer-service Elo (Artificial Analysis)	1,331 ±28
Naturalness (Speko)	1,578
Naturalness estimate (Cekura, 1 to 5)	4.41

Accuracy

Reading accuracy (Cekura)	74.9%
Numbers (Cekura)	71%
Codes (Cekura)	75%
Context (Cekura)	58%
Medical terms (Cekura)	100%
Hard passages judged correct (Artificial Analysis)	74.5%
Numbers and dates (Speko score)	0.21
Word error rate (Coval)	1.5%

Price per 1 million characters

Range across sources	$39.20 to $50
Artificial Analysis	$49
Speko	$50
Coval	n/a
Cekura	$39.20

Coverage

Access	Proprietary
Streaming	Measured
Coval tags	emotion-control, multilingual, voice-cloning
Rated for	Knowledge sharing, Assistants, Entertainment, Customer service
Languages tested	Arabic, Chinese, French, German, Hindi, Japanese, Portuguese, Spanish, Vietnamese

Not collected

Every measure of the database is filled for this model.

Sources

https://artificialanalysis.ai/text-to-speech (read 2026-10-27)
https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read 2026-10-27)
https://benchmarks.cekura.ai/text-to-speech (read 2026-10-27)
https://benchmarks-api-6wxgp27p2a-ue.a.run.app/v1/results/aggregates?benchmark=TTS&window=30d&include_series=false (read 2026-10-27)
https://benchmarks.speko.ai/tts/ (read 2026-10-27)
Vendor site: https://www.cartesia.ai/

Keep exploring

Frequently asked questions

How fast is Cartesia Sonic 3.6?: Coval measures a median time to first audio of 285.8 ms and a P95 of 374.4 ms for Cartesia Sonic 3.6, over 30 days from the US East in English (Visible delay tier).
How much does Cartesia Sonic 3.6 cost?: The benchmarks print a list price of $39.20 to $50 per million characters for Cartesia Sonic 3.6.
Which languages was Cartesia Sonic 3.6 tested in?: Artificial Analysis or Speko tested Cartesia Sonic 3.6 in Arabic, Chinese, French, German, Hindi, Japanese, Portuguese, Spanish, Vietnamese.