Voiceover plus music bed: TTS and Lyria cost, duck_db in Timeline

A 700-character voiceover ($0.03325) and one Lyria bed ($0.125) cost $0.15825 before the render. Timeline duck_db (0 to 20) lowers the bed under speech.

4 min readSume
All posts

A 700-character voiceover plus one music bed costs $0.15825 on Sume before you render: $0.03325 for TTS at $0.0475 per 1,000 characters and a flat $0.125 for one music generation. In Timeline 1.0 the bed goes in soundtrack, where duck_db (0 to 20) lowers it under the voice.

Parts list

The Timeline render itself is priced separately; this table covers only the two audio inputs.

Voiceover and bed inputs (read 2026-10-09)
ItemRateCost
TTS, 700 characters$0.0475 per 1,000 characters$0.03325
Music Router, 1 generation$0.125 flat$0.125
Inputs total$0.15825

The soundtrack object

Use the TTS file as the audio spine and the music file as the bed. duck_db needs a real spine; with silence it fails duck_requires_audio_spine.

{
  "audio": {"url": "<tts audio url>", "duration_seconds": 42},
  "soundtrack": {
    "url": "<music audio url>",
    "gain_db": -6,
    "loop": true,
    "fade_out_seconds": 2,
    "duck_db": 10
  }
}

Gotchas

Both URLs must be Sume-hosted. fade_out_seconds is at most 10, and fades must fit inside the output length. The video[] slots and output block are required in a real request; see the Timeline page for the full program.

Sources

Related posts

More in Media tools

All Media tools posts

Written by Sume