Cartesia Sonic 3.5 Cartesia · text-to-speech (TTS) API

Speed

On Coval's 30-day window ending October 22, 2026 (3,376 runs from US East), Cartesia Sonic 3.5 starts speaking after 280.9 ms on a typical turn (median) and 380.5 ms on a slow turn (P95, the slowest one in twenty). That P95 is 18th lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. On the median it is a tie (gap under 10 ms) with Murf AI Falcon 2. Speko's board plots it at 132 ms time to first audio from US East; its model page reports a 121 ms sweep.

Voice quality

Speko rates its naturalness at 1,574 Elo from blind A/B votes on phone-agent lines (11th highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,191 ±11 Elo (95% interval), 18th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 24th, at 1,200 Elo.

Numbers and dates

Speko's pronunciation test on numbers, dates and currency scores it 0.18 on a 0-to-1 scale (27th highest of the 30 models Speko scores). This is the accuracy measure used here; Coval's word error rate separates models too little to compare them.

Price

Artificial Analysis lists $49. Speko lists about $50. List prices, as each source prints them: a range of $49 to $50.

Languages tested

Tested in Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi, Vietnamese, Korean, Filipino, Norwegian, Tamil, Telugu and Thai by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.