238 ms P50 time-to-first-audio on Speko; ranked 55th (tied) of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 8.1/100, ranked 55th (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: accuracy, 3.9 of 15 points.
Rime arcanav3 is a text-to-speech (TTS) API from Rime, measured by one independent benchmark, Speko.
Overall score
8.1 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Rime arcanav3 ranks 55th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 8.1/100.
Speko measures a P50 TTFA of 238 ms from US East (n=30), dated July 3, 2026: 15th lowest of the 29 models Speko measures.
Speko rates its pronunciation robustness on numbers, dates and currency at 0.35 on a 0-to-1 scale (11th highest of the 28 models Speko rates).
Speko rates its naturalness at 1,429 Elo from blind A/B votes (35th highest of the 41 models Speko rates).
Speko lists a cost of about $40 per 1M characters.
Speko changed its pronunciation robustness between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (0.5, then 0.35): the score uses the average, 0.425. The value shown is the latest.
Tested in Spanish, German and French by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
async Pro v1.0 is a proprietary text-to-speech (TTS) API from Async, measured by one independent benchmark, Artificial Analysis.
StepFun Step TTS 2 (Mar 2026) is a proprietary text-to-speech (TTS) API from StepFun, measured by one independent benchmark, Artificial Analysis.
Google Gemini 2.5 Flash Lite TTS is a proprietary text-to-speech (TTS) API from Google, measured by one independent benchmark, Artificial Analysis.