Python Audio / Voice AI Developer
Budget: $10 – $30 USD
We have a fully built call center dialer with a Node.js WebSocket server ready and waiting. We need one Python script written that loads an open source real-time voice conversion model (RVC preferred), reads live audio chunks in mulaw 8kHz format, softens Nigerian English accents toward neutral American English, and returns processed audio within 150ms. The script communicates with our existing server via stdin and stdout. Full server code provided on hire.
This is accent softening only. Not voice cloning. Not voice replacement.
Requirements:
Experience with RVC or similar real-time speech to speech models
Python audio processing (mulaw/PCM formats)
RunPod GPU deployment experience
Deliverable: One working Python file, tested on a live call, latency under 150ms.
Please include your relevant experience with voice conversion models
This is accent softening only. Not voice cloning. Not voice replacement.
Requirements:
Experience with RVC or similar real-time speech to speech models
Python audio processing (mulaw/PCM formats)
RunPod GPU deployment experience
Deliverable: One working Python file, tested on a live call, latency under 150ms.
Please include your relevant experience with voice conversion models