Developer Needed for Mac Based Speech to Text Application
- or -
Post a project like this£5.0k(approx. $6.2k)
- Posted:
- Proposals: 16
- Remote
- #2658801
- OPPORTUNITY
- Expired
♛React, PHP, Laravel, WordPress, Logo design, App Developer, AWS expert on PPH.
London
♛ TOP Rated ♛ Company world wide with 5500+ Clients : Web/App developer, Brand Identity, Shopify, PHP, Laravel, Codeigniter,Angular/React/Node.js, WordPress, MEAN STACK/ AWS/Gcloud expert
Noida
WordPress I Magento I Shopify I Android and iOS app development| Joomla I Drupal I Prestashop I OpenCart I SWIFT
Kolkata
Web developer, App developer, PHP developer, Java developer, Sharepoint developer, Andriod developer, iOS developer, Augmented reality developer, Net developer, Angularjs developer
London
4569965668076510386517439067551078783191764723431082738324288740229836333380374
Description
Experience Level: Expert
HIGH LEVEL SPECIFICATION
Summary Overview
We are looking to have developed a speech recognition, dictation application that works on a Mac and allows the end user to dictate to their Mac and have that dictation populated into a target application eg. MS Word.
We envisage having a limited application on the users computer to enable / disable listening and a core application cloud based to handle the transcription and deliver back to the end used. However could also see this all being done on the end users computer depending on the best way to architect it. Below assumes option 1 above.
High Level Requirements
- Simple interface on the users desktop / computer to allow them to enable/disable Speech to Text, we’d like the default to be for the transcribed text to be entered wherever the cursor is currently placed. We’re aware some applications may not permit this however compatibility with Office is essential.
- Core application to collect audio input through the computer mic from the user talking/dictating and transcribe the speech to text.
- Should be able to apply formatting by voice eg. Bold, Italic, full stop etc (nice to have feature).
- The text should be delivered into a “target application” on the computer, typically the Microsoft suite eg. Word and where the users cursor is current placed eg. Chrome.
- Should use a library that we are able to extend with our own specialised words eg. medical dictionary.
- Speech to text tool should be scalable without any sort of pay per word or time based model. For example, the API’s that Amazon and Google provide would not work due to the commercial model which is charged based upon volume of transcription, we cannot support a model where we have to pay per transcription or time.
- Works on Mac (priority) and Windows
- To be architected to extend to mobile / tablet in future release.
- Clear privacy controls to clear indicate when the software is enabled and when disabled ie. When it is “listening” and when it isn’t.
Please ignore the below budget - we require proposals for completion of the work once the scope and requirements have been confirmed.
Summary Overview
We are looking to have developed a speech recognition, dictation application that works on a Mac and allows the end user to dictate to their Mac and have that dictation populated into a target application eg. MS Word.
We envisage having a limited application on the users computer to enable / disable listening and a core application cloud based to handle the transcription and deliver back to the end used. However could also see this all being done on the end users computer depending on the best way to architect it. Below assumes option 1 above.
High Level Requirements
- Simple interface on the users desktop / computer to allow them to enable/disable Speech to Text, we’d like the default to be for the transcribed text to be entered wherever the cursor is currently placed. We’re aware some applications may not permit this however compatibility with Office is essential.
- Core application to collect audio input through the computer mic from the user talking/dictating and transcribe the speech to text.
- Should be able to apply formatting by voice eg. Bold, Italic, full stop etc (nice to have feature).
- The text should be delivered into a “target application” on the computer, typically the Microsoft suite eg. Word and where the users cursor is current placed eg. Chrome.
- Should use a library that we are able to extend with our own specialised words eg. medical dictionary.
- Speech to text tool should be scalable without any sort of pay per word or time based model. For example, the API’s that Amazon and Google provide would not work due to the commercial model which is charged based upon volume of transcription, we cannot support a model where we have to pay per transcription or time.
- Works on Mac (priority) and Windows
- To be architected to extend to mobile / tablet in future release.
- Clear privacy controls to clear indicate when the software is enabled and when disabled ie. When it is “listening” and when it isn’t.
Please ignore the below budget - we require proposals for completion of the work once the scope and requirements have been confirmed.
Chris P.
100% (77)Projects Completed
74
Freelancers worked with
77
Projects awarded
54%
Last project
3 Mar 2022
United Kingdom
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies