Vampro Voice Studio brings voice creation and audio tools into your editing workflow. Less file chasing. More room for the story.
Build custom voice references, turn scripts into narration and transform recorded performances.
Work with installed local models, or choose ElevenLabs with your own account when you need it.
Preview the take, send it to a project bin or place it right where your story needs it.
Voice production should feel like part of editing. Three connected steps keep your ideas moving toward the timeline.
Select a timeline or bin clip, import a clean recording, or record a performance. Save a voice reference you have permission to use.
Write a script, convert a performance or repair your audio. Choose local processing or connect your own ElevenLabs account.
Preview your result, save the take and send it to the bin, playhead or selected source clip in your editing workspace.
Play the core tools, from voice previews to cleanup and stem separation.
Start with a clean reference and shape it into a reusable studio voice.
For every moment a voice can make the picture mean more.
MADE FOR YOUR NEXT GREAT TAKE.Explore narration, audition a new voice and keep alternate takes close to your sequence.
Build a familiar voice for video essays, YouTube series, explainers and independent stories.
Develop voice references for campaign concepts, product demos and branded content.
Shape spoken lessons, clean recordings and organize the takes behind your next episode.
From the first reference to the final take, keep the craft in your hands. Built for editors, filmmakers and the people behind the story.
Turn a clean timeline clip, bin asset or imported recording into a reusable voice reference. Name it. Keep it. Bring it into your next story.
Your reference. Your identity.Start with a recorded performance and convert its voice. Work from a clip, uploaded audio or a microphone take, with one place to preview the result.
From recorded speech to a new take.Write narration for your documentary, product film or next upload. Generate English speech with a saved voice and keep each take ready for your edit.
Written for the screen. Made to be heard.Reduce background noise locally. Split vocals and accompaniment into clear stems, then preview the results before they reach your cut.
Clean voice. Clear music. Ready stems.Import a take to your project bin, insert at the playhead or apply it to the captured source clip. The clip-change workflow preserves the original audio for undo.
Stay close to your timeline.Preview, name and organize voice references. Keep generated takes with timing information, track queued jobs and cancel work when your direction changes.
A little order. A lot more flow.Production-ready tools for voice creation, cleanup, stem separation and saved takes. See workflow details
A studio that follows your process. Work with local models on your machine, or bring your ElevenLabs account when your project calls for it.
Generate with installed local models, keep voices and takes on your computer, and continue creating without a cloud voice API.
Set up the editor panel with a local Windows companion and keep your voice tools close to the timeline.
The panel brings your voice tools into the editing workspace, close to your clips and timeline.
The Windows companion handles local processing, model packs, your voice library and saved takes.
Choose a voice reference and start with a script or a recording. Preview, refine and bring the result into your edit.
What the studio does, how it fits your workflow, and how each production tool works.
Vampro Voice Studio is an offline-first voice and audio toolkit for Windows editing workflows. It brings reusable custom voices, text-to-speech, speech-to-speech, voice previews, clip voice changes, noise removal, vocal/music separation and take management into one workspace, with ElevenLabs connection support.
Voice Generator is Vampro’s existing text-to-speech plugin. Voice Studio is a separate product for a broader production workflow: create custom voice references, convert recorded performances, change a clip’s voice, repair audio and manage saved takes. Voice Generator’s downloads, pricing and voice counts do not apply to Voice Studio.
The workflow accepts a selected timeline clip, a project-bin clip or an imported recording as a voice reference. Choose a clean range, name the voice and reuse it for text-to-speech or speech conversion. Use voices you own or have permission to use.
The local workflow is designed to process audio on your Windows computer after the companion and model pack are installed. Local voice generation does not use a cloud API. ElevenLabs is a connected online provider that uses your own API key and sends only the jobs you choose.
Text-to-speech generates a spoken take from a written script and a selected voice. Speech-to-speech starts with a recording or clip and converts its voice, using the source performance as the input. Both workflows feed the same preview, saved-take and timeline handoff process.
Voice Studio includes local spectral noise reduction and two-stem separation for vocals and accompaniment. The workflow lets you preview cleaner speech, vocal stems and music beds before saving the result into your workspace.
Voice Studio targets Windows with the local companion running. The local engine supports NVIDIA, AMD and Intel GPUs with a CPU fallback. Local voice generation is English, processes one source per job up to ten minutes, and outputs mono 24 kHz PCM audio. Retimed or reversed clips are not supported in the direct-source workflow.
Voice Studio is currently in preview as a production studio workflow. Join the waitlist below to get early installer access, rollout notifications, and workflow updates as releases go live.
Vampro Voice Studio gives media teams a focused place to create voices, clean dialogue and prepare stems for the edit.
Join the waitlist for closed preview access, installer releases, and product updates.
