Job Description: You will be responsible for integrating our existing chatbot with voice capabilities (e.g., text-to-speech and speech-to-text), enabling users to have natural, conversational interactions. You should have experience with AI/ML models, chatbot frameworks, and voice APIs.
Key Responsibilities:
1. Integrate chatbot platforms (Dialogflow, Rasa, etc.) with voice assistants (e.g., Google Assistant, Alexa, or custom voice apps)
2. Implement speech-to-text (STT) and text-to-speech (TTS) pipelines using tools like Google Cloud Speech, Amazon Polly, or Azure Cognitive Services
3. Build APIs and services to support real-time voice communication
4. Optimize latency and ensure high-quality conversational flow
5. Collaborate with UX and backend teams for seamless end-user experience
6. Troubleshoot and resolve voice integration issues
Only those candidates can apply who:
1. have minimum 1 years of experience
1 years of experience in AI, NLP, or chatbot development
Strong proficiency in Python, Node.js, or similar backend language
Hands-on experience with STT and TTS APIs (Google, Amazon, Microsoft)
Familiarity with WebRTC, SIP, or Twilio Voice is a plus
Experience with NLP tools and frameworks (Dialogflow, Rasa, etc.)
Ability to design scalable and secure APIs
Excellent problem-solving skills and attention to detail
Mandatory:🔹 Core Technical Skills
Natural Language Processing (NLP)
Dialogflow, Rasa, IBM Watson Assistant
NLTK, spaCy, transformers (Hugging Face)
Speech Recognition (Speech-to-Text - STT)
Google Cloud Speech-to-Text
Azure Speech Services
Amazon Transcribe
Open-source tools: Mozilla DeepSpeech, Whisper
Text-to-Speech (TTS)
Amazon Polly, Google Cloud Text-to-Speech
Azure Speech, IBM Watson TTS
Open-source: Coqui TTS, Festival
Voice Assistant Platforms
Alexa Skills Kit (ASK)
Google Assistant SDK / Actions on Google
Custom voice apps using Twilio, Voximplant, or WebRTC
Programming Languages
Python, Node.js, or JavaScript (for bot logic)
RESTful API development (Flask, Express)
WebSockets for real-time audio communication
Frontend (optional but beneficial)
JavaScript, HTML5 for embedding voice UI in web apps
React or Vue for SPA development with voice UI integration
Annual CTC: ₹ 2,00,000 /year
Voicedots is an AI-powered Voice BOT platform that brings smart, human-like voice interaction to websites. Designed for businesses across education, retail, manufacturing, and services, Voicedots converts website visitors into leads and provides 24/7 multilingual customer support through natural voice conversations in English and major Indian languages. Whether it's guiding a parent on an admissions page, helping a customer find a product, or answering service queries instantly, Voicedots ensures a seamless and engaging user experience hands-free, instant, and intelligent.
