NARS - Voice synthesizer robot
NARS - Voice synthesizer robot presently offers the Custom Voice feature. Custom Voice allows you to prepare a custom voice model utilizing your own sound to make a one-of-a-kind voice. We record our voice for about 20 -80 seconds to read out text as input and it will synthesize his voice as output.
2025-06-28 16:28:39 - Adil Khan
NARS - Voice synthesizer robot
Project Area of Specialization Artificial IntelligenceProject SummaryNARS - Voice synthesizer robot presently offers the Custom Voice feature. Custom Voice allows you to prepare a custom voice model utilizing your own sound to make a one-of-a-kind voice. We record our voice for about 20 -80 seconds to read out text as input and it will synthesize his voice as output. You can utilize your custom voice to synthesize sound by utilizing this Text to User-Speech system.
The goal of the project is to construct a physical robot that can speak with a person using its own trained voice and could be replicated for many enterprises to reduce human errors and increase productivity. In the future, as technology advances and humans become more accustomed to it, consumers will require physical assistance rather than software-based assistance. Robot Nars will target the healthcare market and is designed to interact with the elderly and those isolated by the COVID-19 pandemic. Nars resemblance to a healthcare professional and capacity for social interaction is aimed at relieving the burden of front-line hospital staff overwhelmed during the pandemic. Nars the Robot can actually apply what he learns by solving real-world problems with us humans by analyzing what we perceive. Data visualization helps Nars make impartial decisions, strengthening trust with AI opinions over time.
The goal of the project is to construct a physical robot that can speak with a person using its own trained voice and could be replicated for many enterprises to reduce human errors and increase productivity. In the future, as technology advances and humans become more accustomed to it, consumers will require physical assistance rather than
software-based assistance Our project will mainly focus on the following objectives:
- The system will communicate with the humans in their own voice.
- The system will ask questions and get answers to those.
- The system will play songs from youTube. set alarms, search and read articles from google, check the weather condition.
- The system will help reading and recording purposes (YouTube recorded learning videos, Lecture, News Scripting and FM recordings with clone characters voices, Institute lectures with teachers voices).
- The system will be used for communication in call centers. public services messages, product selling, Insurance services and medical billing.
- The system will be used for public services messages/announcements,product selling, Insurance services and medical billing.
Our system depends on the human sound we gather from the client so that in the wake of giving a passage of text we request that the client read that in their own voice after recording for something like 20 to 60 seconds we will check the pre-record models which we prepared for our system. by contrasting the recorded voice and our pre-train model the system will additionally create the cloned voice to our client. this multitude of system modules will be customized in a python neural network with various Vocoder libraries in it.
Then the customized system will move to the equipment utilizing
Raspberry Pi and different logic-based libraries. people can likewise see the sound range on the LED we implanted in our equipment.
After our cloning part, the system will perform like an assistant in your telephone gadgets, and human clients can speak with our system and get answers to your questions and perform other things too.
Benefits of the Project- All the organizations which are working on the audio casting like FM radio and call centers.
- a voice cloning system will give the better opportunity to Youtube content creators to use their own voices but as a background.
- Cloning systems will help the Film Industry to get their dialogues with their actor voice.
- System will help News Channels to deliver their news with anchors voices.
- System will help educational institutes and learning sites which are giving online recorded lectures.
The final deliverable of " NARS - Voice synthesizer robot" will be an hardware based robot along with documentation manual having all technical details of the hardware. It will be developed in Python Neural Networks along with python assistant program. We will develop a python and api's that we will integrate with our hardware using raspberry pi.
Final Deliverable of the Project Hardware SystemCore Industry ITOther Industries Education , Medical , Media , Others , Telecommunication Core Technology Artificial Intelligence(AI)Other Technologies RoboticsSustainable Development Goals Industry, Innovation and Infrastructure, Responsible Consumption and ProductionRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 70000 | |||
| Voice And Speaker based system (Laptop) | Equipment | 1 | 35000 | 35000 |
| Arduino Uno with IC's chips | Equipment | 2 | 5000 | 10000 |
| Led Screen | Equipment | 1 | 7000 | 7000 |
| Speakers | Equipment | 2 | 2750 | 5500 |
| Noise canceling Microphones | Equipment | 1 | 7000 | 7000 |
| Robot Type Cover | Equipment | 1 | 3000 | 3000 |
| Documentation | Miscellaneous | 5 | 500 | 2500 |