261.3 ms P50 time-to-first-audio on Coval; ranked 22nd of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 33.9/100, ranked 22nd of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: real-time speed, 33.3 of 60 points.
Deepdub Phantom Z 3.4 conversational is a proprietary text-to-speech (TTS) API from Deepdub, measured by one independent benchmark, Coval.
Overall score
33.9 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Deepdub Phantom Z 3.4 conversational ranks 22nd of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 33.9/100.
On Coval's 30-day window ending October 1, 2026 (11,585 runs), Deepdub Phantom Z 3.4 conversational has a P50 (median) time-to-first-audio (TTFA) of 261.3 ms, 14th lowest of the 31 models Coval measures. Its P99, the slowest 1% of turns, is 427.4 ms (14th lowest of the 31 models Coval measures). Latency consistency: a standard deviation of 80.8 ms (12th lowest of the 31 models Coval measures). Mean time to first byte (TTFB) is 241.2 ms.
Coval measures an accuracy (word error rate) of 5.8% over 11,565 samples on the same window, 28th lowest of the 31 models Coval measures.
Neither Artificial Analysis nor Speko rates its voice quality, so it counts 0 of 20.
No price is published by Artificial Analysis or Speko for this model; price counts 0 of 5.
Smallest.ai Lightning V3.1 Pro (Jul 2026) is a proprietary text-to-speech (TTS) API from Smallest.ai, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Fish Audio S2.1 Pro is a proprietary text-to-speech (TTS) API from Fish Audio, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Deepgram Aura 2 is a proprietary text-to-speech (TTS) API from Deepgram, measured by two independent benchmarks: Coval and Speko.