Deepdub Phantom Z 3.4 conversational
Deepdub Phantom Z 3.4 conversational is a proprietary text-to-speech (TTS) API from Deepdub, measured by one independent benchmark, Coval.
300 ms median and 415 ms P95 time to first audio on Coval (30 days to October 22, 2026): Visible delay speed tier.
Benchmark summary: Visible delay speed tier on Coval's P95 (the voice becomes a visible part of the delay).
Rime Coda is a proprietary text-to-speech (TTS) API from Rime, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Speed tier
Visible delayP95 of 320 ms or more. The voice becomes a visible part of the delay.
Data read October 22, 2026. No combined score: methodology
Gradium TTS vs Rime Coda Fastest TTS APIs, by speed tierOn Coval's 30-day window ending October 22, 2026 (1,302 runs from US East), Rime Coda starts speaking after 299.6 ms on a typical turn (median) and 415 ms on a slow turn (P95, the slowest one in twenty). That P95 is 19th 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 Cartesia Sonic 3.6. Speko's board plots it at 148 ms time to first audio from US East.
Speko rates its naturalness at 1,535 Elo from blind A/B votes on phone-agent lines (20th highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,056 ±12 Elo (95% interval), 62nd highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 52nd, at 1,101 Elo.
Speko has not scored its pronunciation of numbers and dates.
Coval lists $50 per 1M characters (since Aug 10, 2026). Artificial Analysis lists $50. Speko lists about $50. List prices, as each source prints them.
Tested in Korean by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
Deepdub Phantom Z 3.4 conversational is a proprietary text-to-speech (TTS) API from Deepdub, measured by one independent benchmark, Coval.
Cartesia Sonic 3.5 is a proprietary text-to-speech (TTS) API from Cartesia, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Cartesia Sonic 3.6 is a proprietary text-to-speech (TTS) API from Cartesia, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.