The company Voctro Labs,S.L., with registered offices in C/ Pujades 74-80, 08005 - Barcelona (Spain), with Tax Identification Number B-65.699.662, registered in the Companies Registry of Barcelona, Volume 42942, Folio 161, Page number B 42023 (hereinafter referred to as “VOCTRO LABS”) is the owner of the web site http://www.voiceful.io (hereinafter referred to as “Web Site”).
Address: C/ Pujades 74-80, 08005 – Barcelona (Spain).
Telephone: +34 931 587 637.
Email: [email protected]
1.- General Terms of Use |
|
2.- Intellectual and industrial property |
|
3.- Limitation of Liability |
|
4.- Governing law and competent courts |
|
Updated in February 2020
|
|
|
|
|
Updated in February 2020
Recent advances in the area of Machine Learning and Artificial Intelligence can be applied to the generation of a human-like voice signals. Given a set of recordings of a speaker or singer of several minutes, we can create a voice model that captures its main treats, including singing expression. Once this voice model is loaded, Voiceful can generate new content. You can refer to the technical details in this research publication.
Manipulating voice recordings have several applications in the creative media industries. Voiceful offers a patented voice transformation technology [Patent Nr.] that can be integrated in real-time (e.g. a plugin for a Unity videogame, audio FX in a DAW) or as batch processing tool in a post-production workflow (e.g. for film, games, animation, TV, music).
Editing a voice recording without altering the original voice quality has been extensively used in music and film productions with tools such as pitch correction and dialogue synchronization. Voiceful provides a tool that analyzes and automatically corrects a voice recording. In film applications, Voiceful can synchronize two voice recordings in the ADR workflow (Automatic Dialogue Replacement). We can use onset and phonetic alignment to generate lip-synched animations. In music, VoAlign allows to automatically estimate the musical key of an a capella recording and applying pitch correction to achieve perfect tuning.
A voice recording conveys an incredible amount of information. For speech, it can be information about the words, about the person, about the emotion; while for singing voice it can bring also information about notes, intonation, the key and tempo of a song. To make clear, Voiceful is not a speech recognition solution. Besides the world of creative media, the analysis algorithms in Voiceful can be further extended for Medical or forensic applications. Check in this example the analysis output and the format of exported data.
Be it a commercial music downmix, be it a field-recording for a film, Voiceful can change the duration and key while preserving the quality of the original recording. Playback speed and transposition controls can be passed dynamically in real-time. For example, the tempo of a song can be changed on the fly synched by a runner's pace, or a gesture movement on a mobile phone. This is a validated professional audio tool, and we are happy when clients with trained ears choose Voiceful over other solutions in the market. Check our demo in this video
This is a utility to automatically mix the contents generated by Voiceful with existing musical or FX background tracks. All parameters are configurable and can be adjusted through our VoMix Editor GUI tool [see screenshot]. VoMix is usually place as tha last process in a multi-stage workflow.
User input is... | What languages? | Processing | |
---|---|---|---|
Synthetic voices | |||
Speech content | Text | ENG, SPA (other languages upon request) |
Batch |
Singing content | Text and/or MIDI, MusicXML | ||
Transformed voices | |||
Speech content | Mic-in or Audio file | Any | Real-time, batch |
Singing content | |||
Voice Description | |||
Speech content | Mic-in or Audio file | Any | Real-time, batch |
Singing content | |||
Pitch and Time change | |||
Speech content | Audio file | Any | Real-time, batch |
Singing content | |||
Audio content |
Supported SDK clients | Architecture | ||||
---|---|---|---|---|---|
Web | Mobile | Desktop Server |
Standalone (on device) |
Cloud API (on server) |
|
JS/PHP* | iOS Android |
Linux OSX Windows |
|||
*Clients also available for Python and Ruby. |
Features | Available on Voiceful | Custom built |
---|---|---|
Synthetic voices | ||
Catalogue: male pop, female pop |
||
Custom: celebrities, artists, personal... |
||
Transformed voices | ||
Human: male, female, child, elder |
||
Fiction: robot, alien, cartoon, monster |
||
Custom: game character, ... |
||
Pitch and Time change | ||
Time-scaling, Pitch-shifting, Pitch Correction, Time Alignment |
||
Voice Description | ||
Voice data analysis | ||
Graphics and design |
Happy Birthday Sing along karaoke track belongs to Allstars kids Club
(c) All Stars Kids Club
Let It Go is a song from Disney's 2013 animated feature film Frozen
(c) Disney
Voiceful is a toolkit that uses voice technology to create new ways of expressing yourself.
You write or customize the lyrics, and an incredibly expressive voice sings it for you.
Commission us your own voice model, be it a famous or a beloved one, be it dead or alive.
Sound like a robot. Sound like your son. Sound faster, or chilled. Do some voice lifting.
Everyone is gifted with a hidden talent. Sound like you can sing and share it to the world.
Voiceful provides AI Voice solutions for creative apps, games and media content productions.
Our Cloud API is a RESTful API that can be easily integrated into web sites, mobile apps and other SaaS platforms.
Our Standalone SDK can be integrated as cross-platform C++ libraries for Mobile (iOS/Android), Desktop or Server applications.
We offer Custom Services to extend and customize our technologies for the specific needs of your project idea.
Happy Birthday to you
Happy Birthday to you
Happy Birthday,
Happy Birthday to you
Let it go, let it go
Let it go, let it go
Click on the text box to change lyrics.