Voice Isolator Models by Inworld

InworldApache 2.0Open source
Inworld releases · 3 in the last 12 months · this family litChangelog →
2 models2026

Last refreshed 2026-11-19. Next refresh: weekly.

Details

ResearcherInworld
LicenseApache 2.0OSI-approved
Commercial usePermitted
Models2
Released2026

Links

Website

About

Inworld’s offline and streaming speech-denoising models.

Decision facts

Best fit
speech enhancementcoding
Capability starting point
Voice Isolator v1
Lowest tracked input
Not tracked
Closest related family
SAVA

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs speech enhancement, 64M parameters, and audio.

2026-11speech enhancement64M parametersaudio

Use when the workload needs speech enhancement, 58M parameters, and audio.

2026-11speech enhancement58M parametersaudio

Release Timeline

1 release group
2026-11
2 current
Voice Isolator v1
speech enhancement64M parametersaudio
Current
Voice Isolator v1 Realtime
speech enhancement58M parametersaudio
Current

Specifications(2 models)

Voice Isolator model specifications comparison
ModelReleasedParameters
Voice Isolator v12026-1164M
Voice Isolator v1 Realtime2026-1158M