Fit a voiceover to 30 seconds: tune TTS speed between 0.6 and 1.5

generation_config.speed runs 0.6 to 1.5 on Sume TTS. Three takes of a 450-character script cost $0.064125 total, so measure the file and retune.

4 min readSume
All posts

To fit a voiceover into a 30-second slot, set generation_config.speed (0.6 to 1.5) on Sume TTS and retake until the file fits; three takes of a 450-character script cost $0.064125. Each take is $0.021375 at $0.0475 per 1,000 characters.

Retake math

Speed is a multiplier, so a take that runs 36 seconds at 1.0 needs about 36 / 30 = 1.2. Round up a little, then verify. This is arithmetic on the measured file, not a model guarantee.

Sume TTS, 450-character script, retakes (read 2026-10-09)
TakeSpeedMeasured length (example)Cost
11.036 s$0.021375
21.230.4 s$0.021375
31.2529.2 s$0.021375
All three$0.064125

Request body

Keep the transcript, voice and language fixed so only speed changes, and key each take separately (vo-30s-take2).

{
  "transcript": "Meet the lightest rain jacket we have ever made. ...",
  "avatar_handle": "@narrator",
  "language": "en",
  "generation_config": {"speed": 1.25, "volume": 1.0},
  "metadata": {"take": 3}
}

Gotchas

The top-level speed field (slow, normal, fast) is deprecated; use generation_config.speed. Speeds near 1.5 can sound rushed, so if you need more than about 1.3, cut words instead. The 30-second target is yours; a Shorts clip can run up to 3 minutes per YouTube's own help page, so 30 seconds is a design choice.

Sources

Related posts

More in Media tools

All Media tools posts

Written by Sume