FeaturesProductsCustomersAboutSupport

VoiceQ AI

AI that works where your content lives — on your device

VoiceQ AI pairs secure on-device transcription and lip-sync video analysis with leading third-party services for translation and text-to-speech. Confidential, fast, and built into VoiceQ Pro and Writer.

Powered by Apple silicon · Zero data sent to the internet · ~82% less script adaptation time vs a manual workflow

On-device AI transcription

Confidential, fast transcription — no servers involved

VoiceQ transcribes audio using Apple's native silicon (Siri/Dictation), so nothing leaves your machine. No external server communication, processing at local-device speed, and setup is as simple as creating a project, importing audio, and selecting "Transcribe using on device AI."

Confidential & secure
Local processing
Easy setup

On-device AI video analysis

Computer vision for lip-sync dubbing and ADR

VoiceQ analyses your picture and marks the timing points that matter for sync: when characters are on or off screen, the exact "open mouth" and "close mouth" moments, and every video cut on the timeline.

Facial detection
Mouth detection
Scene detection

Beyond the device

Third-party services and AI Sync

On-device AI covers transcription and video analysis. For translation, text-to-speech and character-differentiated transcription, VoiceQ connects to the services you already trust.

Third-party integrations

Configure advanced translation and text-to-speech services via Window > External Service Configuration (Command+6), and use them alongside the on-device tools.

XL8
Google Cloud Translation
Veritone
DeepL

AI Sync Conversation

After recording a line in the new language, one click on the take's Actions button (the "A" with dots) analyses the voice and synchronises the audio with the translated script — no manual word alignment, with up to 70% less time spent on lip-sync word timings.

Built into Pro & Writer

VoiceQ AI isn't a separate product — every capability here ships inside VoiceQ Pro and VoiceQ Writer on macOS. See plans and pricing to pick your fit.

The VoiceQ AI workflow

From imported audio to synced dialogue, step by step

Four stages take a project from raw media to perfectly timed, translated dialogue — the first two entirely on your device.

Stage I

On-device transcription

  1. Create a project and import audio in VoiceQ Pro or Writer.
  2. Go to Script > AI Options and choose "Transcribe using on device AI."
  3. Review and finalise the script, then allocate characters. For character-differentiated transcription, use a third-party service like XL8.

Stage II

Video analysis

  1. Go to Script > AI Options and choose "Video Analysis…" for the full video or a selected range.
  2. Pick a quality/speed balance — 100% (Every Frame) for highest accuracy — and tick Scene Detections and Facial Detection.
  3. Optionally fine-tune Open Mouth Size Ratio (low) and Facial Landmarks Confidence (very high) for precise markers.
  4. Review with Marker Navigation (Command+5) to jump straight to each marked moment.

Stage III

Third-party services

  1. Open Window > External Service Configuration (Command+6).
  2. Connect XL8, Google Cloud Translation, Veritone or another provider for translation and text-to-speech.

Stage IV

AI Sync Conversation

  1. Record a line in the new language.
  2. Click the take's Actions button ("A" with dots).
  3. The AI analyses the voice and syncs the audio to the translated text — no manual word alignment.

Start your project today

Our paid trial gives you and your team full access. Create a project in minutes.