Learn the workspace.
Follow the workflow.

Download the installer for your operating system and complete the installation.

Review the Software License Agreement, choose your preferred interface language, then select Accept and continue.

Enter the purchase email and VOX license key exactly as shown on your order confirmation.

After activation, use About → License to review the plan and activation status.

Choose Text to Speech to create voice from a written document.

Choose Speech to Text to begin a new microphone, desktop-audio, or imported-audio transcript.

Open Projects to return to saved Text to Speech or Speech to Text work.

Open Queue to review processing progress, completed jobs, and retryable failures.

Open Text to Speech and select the title at the top of the page to rename the project.

Enter the script in the document canvas. A project is saved after it contains text.

In Engine, choose a connected voice, language, speed, pitch, loudness, and word-pause timing.

Use the bottom Play control to synthesize and play the complete document.

Highlight a word, sentence, or passage in the canvas, then right-click the selection.

Open Engine to set a selection-specific voice, speed, pitch, or loudness.

Choose Emphasis → Reduced, Moderate, or Strong, or open Effects for soft voice, breathing, whisper, dynamic-range control, and timbre shaping.

Choose Play in the context menu to synthesize and hear only the selected passage.

Open Pronunciation and add the written word or phrase together with the replacement that should be spoken.

Edit an existing rule when the spoken result needs adjustment. Enabled rules are reused during synthesis.

Return to the document and play the affected passage or the full document to verify the result.

Select Export Audio, then choose WAV, audio-only MP4, OGG, or WebM and save the file.

Open Provider connections and select the Speech to Text tab.

Review each model’s size and expected performance, then download the model suited to your device.

Wait for the download and verification to complete before opening Speech to Text.

Select the installed model and the language spoken in the recording.

Choose Microphone for your voice, Desktop audio for system playback, or Upload audio for a recording.

Select the input device, language, local model, and expected number of speakers.

Start recording. Interim words appear in the canvas while stable segments are committed during capture.

Switch capture sources when needed; committed transcript text remains in the same project.

Before capture, choose the expected speaker count from 1 to 10.

After recording, let local diarization add generic speaker labels to the detected segments.

Review the canvas, correct the transcript, and rename speaker labels where needed.

Save the project, then reopen it later from Projects → Speech to Text.

Open Projects and switch between the Text to Speech and Speech to Text tabs.

Select a project to continue editing, previewing, transcribing, or exporting it.

Use Delete only when the confirmation dialog identifies the project you intend to remove.

Open Queue to inspect active jobs, retry a failed operation, or review completed work.

Open Provider connections and select a Text to Speech provider.

Read its credential instructions, pricing link, and supported capabilities.

Enter the required credentials and save the connection.

Return to Text to Speech; the Engine lists only connected providers and the voices and languages they report.

Open Settings to change language, theme, recording behavior, retention, storage, and application data preferences.

Open About → Update to check for and install an available application release.

Open About → License to review the active plan or deactivate this installation.

Open About → Help for WhatsApp Support, User Guide, and Feedback.