Audio samples on https://diffio.ai/remove-reverb-from-audio/

Each "original" is the clip uploaded to Diffio. Each "pro" file is the unedited restored speech that the
Diffio API returned with Diffio 4.6 Pro on November 3, 2026, with no background mixed back in. The only change to
either file is one fixed gain so both sides of a pair play at the same integrated loudness. The restored files
are adaptations of their sources and carry the same license.

[reverb-01]
Sample made by playing clean speech (LibriTTS, CC BY 4.0) through a real measured impulse response of a large lecture room (room D105, BUT Speech@FIT Reverb Database, Brno University of Technology, CC BY 4.0). Restored with Diffio 4.6 Pro. Both clips are loudness-matched for playback.
- clean speech: LibriTTS test-clean speaker 2830, utterances 2830_3980_000016_000001 to 2830_3980_000016_000008, LibriTTS (Zen et al., 2019), from a public-domain LibriVox reading. https://www.openslr.org/60/ (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/)
- room impulse response: BUT Speech@FIT Reverb Database, room D105 (lecture room, about 2,000 m3), Brno University of Technology, Speech@FIT (Szöke et al., 2019). https://speech.fit.vut.cz/software/but-speech-fit-reverb-database (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/)
Files: reverb-01-original.mp3, reverb-01-pro.mp3

[reverb-02]
Sample made by playing clean speech (LibriTTS, CC BY 4.0) through a real measured impulse response of a lecture room with the microphone far from the talker (room E112, BUT Speech@FIT Reverb Database, Brno University of Technology, CC BY 4.0). Restored with Diffio 4.6 Pro. Both clips are loudness-matched for playback.
- clean speech: LibriTTS test-clean speaker 5683, utterances 5683_32865_000045_000000 to 5683_32865_000045_000003, LibriTTS (Zen et al., 2019), from a public-domain LibriVox reading. https://www.openslr.org/60/ (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/)
- room impulse response: BUT Speech@FIT Reverb Database, room E112 (lecture room, about 900 m3), distant microphone, Brno University of Technology, Speech@FIT (Szöke et al., 2019). https://speech.fit.vut.cz/software/but-speech-fit-reverb-database (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/)
Files: reverb-02-original.mp3, reverb-02-pro.mp3

[real-room-echo]
Real recording: Carolyn Hewson delivering the 2026 Joseph Fisher Public Lecture at Adelaide University, recorded by Pangalau, CC0, via Wikimedia Commons. Restored with Diffio 4.6 Pro. Both clips are loudness-matched for playback.
- real recording: Carolyn Hewson delivering the 2026 Joseph Fisher Public Lecture at Adelaide University, Pangalau (recordist); speaker Carolyn Hewson. https://commons.wikimedia.org/wiki/File:Carolyn_Hewson_delivering_the_2026_Joseph_Fisher_Public_Lecture_at_Adelaide_University.ogg (CC0 1.0, https://creativecommons.org/publicdomain/zero/1.0/)
Files: real-room-echo-original.mp3, real-room-echo-pro.mp3