184.8 ms P50 time-to-first-audio on Coval; ranked 11th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 56.1/100, ranked 11th of 112 in the TTS for Voice Agents 2026 index (Strong). Strongest criterion: real-time speed, 45.7 of 60 points.
ElevenLabs Flash v2.5 is a proprietary text-to-speech (TTS) API from ElevenLabs, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Overall score
56.1 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
ElevenLabs Flash v2.5 ranks 11th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 56.1/100.
On Coval's 30-day window ending October 1, 2026 (11,842 runs), ElevenLabs Flash v2.5 has a P50 (median) time-to-first-audio (TTFA) of 184.8 ms, 8th lowest of the 31 models Coval measures. Its P99, the slowest 1% of turns, is 332.4 ms (8th lowest of the 31 models Coval measures). Latency consistency: a standard deviation of 33.2 ms (4th lowest of the 31 models Coval measures). Mean time to first byte (TTFB) is 148.2 ms.
Coval measures an accuracy (word error rate) of 6.5% over 11,822 samples on the same window, 30th lowest of the 31 models Coval measures.
In the Artificial Analysis Speech Arena (capture of October 1, 2026), ElevenLabs Flash v2.5 has an Elo of 1,076 (±11, 95% confidence) from 5,643 blind comparisons, 45th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,494 Elo from blind A/B votes (27th highest of the 41 models Speko rates).
Artificial Analysis lists ElevenLabs Flash v2.5 at $50 per 1M characters (57th lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $50 per 1M characters.
Tested in Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi and Vietnamese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
ElevenLabs Eleven v3 Conversational is a proprietary text-to-speech (TTS) API from ElevenLabs, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
SpeechifyAI Simba 3.2 is a proprietary text-to-speech (TTS) API from Speechify, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Soniox TTS RT v1 is a proprietary text-to-speech (TTS) API from Soniox, measured by two independent benchmarks: Coval and Speko.