Starfish Technologies has announced voice-synthesis support for the forthcoming version 9 of its Advantage AD audio-description workstation. Completed scripts can be sent to compatible services through Windows SAPI 5.3 or the ElevenLabs API to generate a narration track.
The existing production model remains available: teams can prepare the timing and script inside Advantage and record a human narrator. The new option is intended to provide another route for versions, lower-volume titles or workflows where synthetic speech is appropriate.
Why it matters
Audio description is a specialised accessibility workflow with significant timing and production overhead. Direct synthesis inside the authoring workstation can remove file transfers and help producers compare voices or create additional language versions, provided editorial review remains part of delivery.
Synthetic performance may struggle with names, emotion, pacing and culturally specific pronunciation. Starfish has not announced a release date, pricing or quality-assurance mechanism, and use of a cloned or branded voice also raises consent and rights questions beyond technical compatibility.
