Hear the difference

Compare three low-quality VoxCPMTTS samples before and after Sidon restoration. Play either version in each pair to hear the difference.

Spoken text

Give your voice a cleaner finish with Sidon, local audio restoration that helps rough recordings sound their best.

Sample 1

Before

Original · low quality

VoxCPMTTS output before restoration.

Download sample 1 · Opus
After Sidon

Restored voice

The recording with Sidon applied.

Download sample 1 · Opus

Sample 2

Before

Original · low quality

VoxCPMTTS output before restoration.

Download sample 2 · Opus
After Sidon

Restored voice

The recording with Sidon applied.

Download sample 2 · Opus

Sample 3

Before

Original · low quality

VoxCPMTTS output before restoration.

Download sample 3 · Opus
After Sidon

Restored voice

The recording with Sidon applied.

Download sample 3 · Opus

Only one recording plays at a time, including across samples. Use the players to pause, seek and adjust volume.

About these recordings

All recordings are mono at 48 kHz. Sample 1 is approximately 7.7 seconds long; samples 2 and 3 are approximately 5.8 seconds each. Both original and restored recordings are served as Opus, encoded with the same 96 kbps variable-bitrate settings. Their decoded durations differ by about two milliseconds, retained from the supplied files. No gallery loudness matching was applied. These are listening examples, not a general quality benchmark.

Sidon resynthesizes speech and may change timbre or introduce artifacts. Compare your own voices and settings. See the studio overview, performance measurements and runtime qualification.