Real-Time Voice AI Engineer — Whisper, TTS, WebRTC, Twilio

Job Type:

45-day contract

About the Role:

You will build the real-time audio layer — live voice → STT → agent → TTS → voice output.
You will NOT access AI logic or backend model weights.

Responsibilities:

• Build LiveKit or Twilio-based voice streaming
• Implement Whisper STT Streaming
• Integrate TTS (ElevenLabs, PlayHT, Cartesia, XTTS v2)
• Handle low-latency audio pipelines
• Call routing, PSTN bridging
• Implement no-speech handling, retries, fallbacks

Qualifications:

• WebRTC / WebSockets / LiveKit experience
• Whisper STT experience
• Twilio Voice API experience
• Python or Node.js streaming background

Job Type: Contract
Contract length: 45 days

Pay: Rs120,000.00 - Rs180,000.00 per month

Work Location: Remote