SpeechTrack: Live Voice Clone

Your voice in English, Mandarin, or Cantonese. Choose how Chinese text is spoken, mix languages, and use one voice library for Studio and timed narration.

SpeechTrack is an on-device voice studio and timed narration editor. Create a voice for English, Mandarin, or Cantonese speech from your own permitted audio, then type and hear it speak or build one polished audio track with exact timing.

VOICE STUDIO Use a 5–15 second clear English, Mandarin, or Cantonese recording or imported audio file. In Live mode, new text speaks automatically after you pause typing. In Complete mode, prepare the whole message and speak when you are ready. Read Traditional or Simplified Chinese, including English words inside Chinese text, and explicitly choose Mandarin or Cantonese pronunciation when Chinese characters are present. Save everyday phrases for reuse and choose from the same Voice Library as your projects. Studio remembers your selected voice; renames and reference updates apply everywhere. Voice samples, profiles, text, and generated audio stay on your device.

Free use includes one saved voice in the shared Voice Library and 3 minutes of generated Studio speech in your first week on each device, then 30 seconds each week, shared across Live and Complete. Weeks run in seven-day periods from first launch; unused time does not roll over. Voice setup and editing remain free. SpeechTrack Pro Lifetime removes the Studio speech limit and saved-voice limit for existing and new Pro customers.

TIMED NARRATION Write a script, place each segment on an exact timeline, choose a local Apple system voice or a voice you created, then preview or export the result. It is made for presentation rehearsals, product demos, training, classroom lectures, onboarding, and repeatable narration.

For project narration, free use lets you keep one cloned voice and create previews or exports with up to 30 seconds of estimated speech. Apple system and cloned voices both count; timeline silence does not. SpeechTrack Pro Lifetime removes both project limits.

FEATURES • Live type-to-speech after a short typing pause • Complete mode for full messages • Reusable saved phrases • On-device English, Mandarin, and Cantonese voice creation from a short recording or audio file • Local Apple system voices and adjustable speech speed • Exact start times, with optional leading and trailing silence • M4A, WAV, or AIFF export when supported by the device • CSV import and export for spreadsheet workflows • Saved project versions before you retime or rewrite • Control whether overlapping segments mix or move into sequence

SpeechTrack works without an account or cloud voice service. Only create or copy a voice you own or have explicit permission to use.