Features
PLUG-IN
VoiceWunder is a state-of-the-art ARA2 Plug-In, that seamlessly integrates into your familiar production environment (currently supporting Avid Pro Tools, Steinberg Nuendo/Cubase, Apple Logic Pro, Presonus Studio One Pro and Cockos Reaper). It offers speech synthesis with TTS, STS, voice cloning, voice design/remixing and denoising in outstanding quality and impressive speed – all without leaving your DAW. Also available: STT (speech-to-text) to transcribe your recordings.
Simply register, install the plug-in, and get started.
VOICES
VoiceWunder offers a curated library of international voices for your projects. Additionally, you can train your own voices – simply upload 1-5 minutes of reference material and get started. You can also design your own custom voice from scratch by using descriptive text prompts or remix the voices by simply prompting the desired changes. All voices speak up to 74 languages. A full commercial license for all voices in the library is included in the Basic and Studio plans. This usage remains valid even after the subscription ends. Important: The prerequisite for cloning a voice is the explicit consent of the respective speaker.
WUNDER BUTTON
Simply hit the WUNDER BUTTON and watch VoiceWunder effortlessly remove background noise from poor-quality original audio. Thanks to its highly advanced adaptive algorithm, no additional settings are required. This essential tool saves both time and money on every dialogue edit. Quite simply, it’s a true Wunder.
VOICE SHARING
Voice Sharing allows voice talents with a Voice Talent plan to create licensed versions of their own voice and make them available to selected users with a Studio plan. These voice variants can represent different speaking styles, tonal characteristics, or production contexts and are managed in the voice talent’s dashboard.
In the dashboard, the voice talent creates and manages voice versions, grants access to studios, and can review all voice activity. Ownership of the voice remains with the talent at all times, and access can be revoked at any time.
Studios with access can generate speech using the shared voice for layouts, adaptations, and productions without requiring a separate recording session. This allows existing voice relationships to continue across different production stages while maintaining the original voice.
All voice activity is logged and visible to the voice talent in the dashboard, including when the voice was active and what content was created. Usage rights, license scope, and compensation are agreed directly between the voice talent and the studio. Voice Sharing provides the technical infrastructure for this workflow and integrates into existing production environments without requiring dedicated software.
VOICE OVERS
VoiceWunder allows you to effortlessly generate professional voice within your familiar production environment. With TTS, simply enter the desired text, choose a voice, and render the speech directly in the plug-in. If you need a different emphasis, regenerate the sentence (or part of it) with ease. The text remains editable even after rendering! Adjust speech speed on the fly.
STS lets you effortlessly swap out a recorded voice while perfectly preserving the original emphasis and tempo – 100%.
FILM POST PRODUCTION
In the world of film, a single imperfect line can break the illusion – and traditionally, that meant bringing the actor back to the studio for an expensive pickup session. Not anymore. With clean source recordings, you can train the actor’s voice and seamlessly replace flawed lines using TTS or STS speech synthesis – preserving the soul of the original performance. But VoiceWunder goes further: effortlessly create perfectly native walla, off-screen voices and small roles in seconds. From subtle ambient chatter to spontaneous minor characters, everything comes to life with cinematic authenticity in up to 74 languages.
COMMERCIALS
When a script changes after the voice talent has left the studio, VoiceWunder makes updates easy. Simply train a voice clone using the original recordings and generate the revised lines with TTS or STS. This saves time and money, maximizes flexibility, and delivers outstanding results – for you and your clients. You can also create a library of your most frequently used voices, allowing you to respond quickly or continue working even if the voice talent is unavailable due to illness, vacation, or high costs. Additionally, VoiceWunder lets you quickly create layouts for your clients. Even casting with the final script becomes smooth and stress-free.
PLUG-IN
VoiceWunder is a state-of-the-art ARA2 Plug-In, that seamlessly integrates into your familiar production environment (currently supporting Avid Pro Tools, Steinberg Nuendo/Cubase, Apple Logic Pro, Presonus Studio One Pro and Cockos Reaper). It offers speech synthesis with TTS, STS, voice cloning, voice design/remixing and denoising in outstanding quality and impressive speed – all without leaving your DAW. Also available: STT (speech-to-text) to transcribe your recordings.
VOICES
VoiceWunder offers a curated library of international voices for your projects. Additionally, you can train your own voices – simply upload 1-5 minutes of reference material and get started. You can also design your own custom voice from scratch by using descriptive text prompts or remix the voices by simply prompting the desired changes. All voices speak up to 74 languages. A full commercial license for all voices in the library is included in the Basic and Studio plans. This usage remains valid even after the subscription ends.
denoise
Simply hit the WUNDER BUTTON and watch VoiceWunder effortlessly remove background noise from poor-quality original audio. Thanks to its highly advanced adaptive algorithm, no additional settings are required. This essential tool saves both time and money on every dialogue edit. Quite simply, it’s a true Wunder.
VOICE SHARING
With the Voice Talent plan, voice talents can create up to 20 digital clones of their own voice and make them available to selected VoiceWunder users with a Studio plan. These voice variants can be used to represent different emphasis styles, moods, or tonal characteristics.
By making their voice available in this way, voice talents can take on additional projects without the need for repeated recording sessions, which may increase the likelihood of being booked by producers they work with regularly.
Access to shared voices is granted and managed exclusively by the voice talent. Ownership of the voice always remains with the talent, and VoiceWunder does not license or resell shared voices. All usage rights are agreed directly between the voice talent and the authorized user.
Unlike standard VoiceWunder speech synthesis, Voice Sharing includes activity logging. This allows voice talents to see which user generated which speech output, and when – as if the voice talent had been present in the studio.
The voice can be cloned conveniently within the DAW, but also via a simple browser upload. Sharing and managing voices is handled exclusively through the talent’s user area in the browser. This means no dedicated software is required for voice sharing.
Voice Sharing is available for voice talents with the Voice Talent plan. Shared voices can be used exclusively by users with a Studio subscription. Use of Voice Sharing requires a signed opt-in from the voice talent or the respective production partner.
Detailed information is available for the following roles:
USE CASES
VOICE OVERS
VoiceWunder allows you to effortlessly generate professional voice within your familiar production environment. With TTS, simply enter the desired text, choose a voice, and render the speech directly in the plug-in. If you need a different emphasis, regenerate the sentence (or part of it) with ease. The text remains editable even after rendering! Adjust speech speed on the fly.
STS lets you effortlessly swap out a recorded voice while perfectly preserving the original emphasis and tempo – 100%.
FILM POST PRODUCTION
In the world of film, a single imperfect line can break the illusion – and traditionally, that meant bringing the actor back to the studio for an expensive pickup session. Not anymore. With clean source recordings, you can train the actor’s voice and seamlessly replace flawed lines using TTS or STS speech synthesis – preserving the soul of the original performance. But VoiceWunder goes further: effortlessly create perfectly native walla, off-screen voices and small roles in seconds. From subtle ambient chatter to spontaneous minor characters, everything comes to life with cinematic authenticity in up to 74 languages.
COMMERCIALS
When a script changes after the voice talent has left the studio, VoiceWunder makes updates easy. Simply train a voice clone using the original recordings and generate the revised lines with TTS or STS. This saves time and money, maximizes flexibility, and delivers outstanding results – for you and your clients. You can also create a library of your most frequently used voices, allowing you to respond quickly or continue working even if the voice talent is unavailable due to illness, vacation, or high costs. Additionally, VoiceWunder lets you quickly create layouts for your clients. Even casting with the final script becomes smooth and stress-free.
AI accelerates. Humans decide.
Built for real-world voice production.
Built for real-world voice production.
All prices are net prices and may be subject to applicable taxes.
Our services are intended exclusively for businesses, freelancers, voice talents, and professional users.
Private consumers are not eligible to use our services.
Powered by VoiceWunder® & ElevenLabs.
Voice creation requires speaker consent.