Skip to content

Tuning by measurement

Chatterbox exposes three settings that shape the voice:

Setting What it does Too low Too high
exaggeration Expressiveness / emotional intensity Flat, “reading” voice Over-acted, unstable
cfg_weight How strongly generation follows the guidance Loose, follows the reference’s pace and accent Slow, over-articulated
temperature Randomness when sampling speech tokens Monotone, repetitive Erratic

I can’t judge a voice by ear for every combination, so I scored them.

Each combination generated the same three Hindi chunks with fixed seeds, scored on:

  • Speaker similarity to the reference (the model’s own voice encoder).
  • Pitch movement: how much the voice rises and falls, compared with the real speaker.
  • Pace: onset rate (a syllable proxy) compared with the real speaker.
  • Failed chunks, from the new chunk check.
Speaker similarity (stable settings vs 0.65)higher is better
  • 0.5 / 0.4 (chosen)0.946
  • 0.4 / 0.30.950
  • 0.65 / 0.40.957
  • 0.65 / 0.50.955

exaggeration / cfg_weight at temperature 0.75. The 0.65 rows look best, but read on.

Re-running the two best stable options with a second set of random seeds:

Settings Similarity Pitch movement (reference 5.53) Failed chunks
0.5 / 0.4 / 0.75 (chosen) 0.946 – 0.955 3.2 – 4.3 0 of 6
0.4 / 0.3 / 0.85 0.952 – 0.955 3.7 – 4.8 1 of 6

Changing only the seed moved the scores as much as changing the settings. The chosen values were the only ones with no failures, so they stayed.

Every stable setting is still a little flatter than the real speaker (about 30% less pitch movement), because the model takes speaking style from only 6–10 seconds of reference. The biggest remaining lever is a better reference recording (15–30 s of natural, expressive speech, no clipping, quiet room), not more tuning.

Next: why it isn’t online 24/7.