Nodes/MuseVoiceSwap/Muse Voice Room Match
ComfyUI Node

Muse Voice Room Match

Makes multiple separately-cloned voices sound like they were recorded together in the same physical space: shared loudness target, one synthesized reverb impulse response convolved identically into every voice, and an optional shared room-tone bed. Pick an environment preset (Room, Hall, Auditorium, Jazz Club, Rock Arena, Cathedral, Outdoor, Studio Dry) the same way you'd pick a reverb preset on a consumer audio system.

By muse-collective-26·Created 2 months ago·Updated about a month ago· 1
Muse Voice Room Match
  • voice_1
  • voice_2
  • voice_3
  • voice_1_out
  • voice_2_out
  • voice_3_out
environmentroom
target_lufs-20.0
wet_level-1.00
room_tone_level0.000
seed0
CategoryMuse Collective

Inputs (8)

NameTypeDefaultDescription
voice_1AUDIOFirst voice to blend into the shared space.
environmentCOMBOroomShared acoustic space applied IDENTICALLY to every connected voice -- same reverb impulse response, same room tone -- which is what actually sells 'recorded together', not matching pitch/tone (not possible between different voices without changing who it sounds like).
target_lufsFLOAT-20.0-40–0Common loudness target all voices are matched to before the shared reverb is applied.
wet_levelFLOAT-1.00-1–1Reverb wet mix override. -1 = use the environment preset's own default wet level.
room_tone_levelFLOAT0.0000–0.1Shared, very quiet background noise bed mixed identically into every voice (0 = off).
seedINT00–2147483647Same seed = same synthesized room impulse response/room-tone every run.
voice_2optAUDIOSecond voice, blended into the same shared space as voice_1.
voice_3optAUDIOThird voice, blended into the same shared space as voice_1.

Outputs (3)

NameTypeDescription
voice_1_outAUDIO
voice_2_outAUDIO
voice_3_outAUDIO