Speech Arena Elo 1,074 on Artificial Analysis, latency not measured; ranked 76th (tied) of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 5.1/100, ranked 76th (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 5.1 of 20 points.
OpenAI GPT-Realtime-2 is a proprietary text-to-speech (TTS) API from OpenAI, measured by one independent benchmark, Artificial Analysis.
Overall score
5.1 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
OpenAI GPT-Realtime-2 ranks 76th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 5.1/100.
Neither Coval nor Speko measures OpenAI GPT-Realtime-2's latency, so it scores 0 of 60 on real-time speed and does not appear in the real-time ranking.
No accuracy measurement: Coval does not measure its word error rate and Speko does not rate its pronunciation robustness, so accuracy counts 0 of 15.
In the Artificial Analysis Speech Arena (capture of October 1, 2026), OpenAI GPT-Realtime-2 has an Elo of 1,074 (±13, 95% confidence) from 2,022 blind comparisons, 46th highest of the 92 models Artificial Analysis rates.
Artificial Analysis lists OpenAI GPT-Realtime-2 at $191.6 per 1M characters (78th lowest of the 78 models Artificial Analysis lists a price for).
Artificial Analysis changed its Speech Arena Elo between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (1,077, then 1,074): the score uses the average, 1,075.5. The value shown is the latest.
Fish Audio OpenAudio S1 Mini is an open-weights text-to-speech (TTS) API from Fish Audio, measured by one independent benchmark, Artificial Analysis.
ElevenLabs Flash v2 is a text-to-speech (TTS) API from ElevenLabs, measured by one independent benchmark, Speko.
MiniMax T2A-01-HD is a proprietary text-to-speech (TTS) API from MiniMax, measured by one independent benchmark, Artificial Analysis.