Speech in
Voice audio is processed for speech recognition as part of the interpretation pipeline.
Discord voice translator
Gloslyn combines its core automatic text translation with optional realtime voice interpretation. Voice is a separate add-on, independently entitled and metered, so communities can use text without being forced into voice costs.
Voice audio is processed for speech recognition as part of the interpretation pipeline.
Recognized speech is translated into the target language using the configured voice flow.
Translated text can be rendered as speech for the destination voice experience.
Text translation remains fully usable without Voice. Voice availability depends on the workspace entitlement and quota, with its usage tracked separately from text characters.
Realtime voice systems are sensitive to network conditions, accents, background noise, recognition quality, translation quality, and synthesis latency. Gloslyn does not claim human-interpreter perfection.
Start with language-specific text channels and add Voice when your community needs it.
See the Discord translator bot →