Hume AI Octave 2 Hume AI · text-to-speech (TTS) API

Speed

Speko's board plots it at 435 ms time to first audio from US East; its model page reports a 448 ms sweep.

Voice quality

Speko rates its naturalness at 1,377 Elo from blind A/B votes on phone-agent lines (41st highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,055 ±12 Elo (95% interval), 63rd highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 69th, at 1,065 Elo.

Numbers and dates

Speko's pronunciation test on numbers, dates and currency scores it 0.24 on a 0-to-1 scale (21st highest of the 30 models Speko scores). This is the accuracy measure used here; Coval's word error rate separates models too little to compare them.

Price

Artificial Analysis lists $87.5. Speko lists about $100. List prices, as each source prints them: a range of $87.5 to $100.

Languages tested

Tested in Spanish, German, French and Japanese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.