
Quicky Prime
TunisiePublication : 18 nov. 2026
[Project-08] - Multilingual Speech AI
- Stage
- 4-6 mois
- Présentiel
- Échéance : 2 déc. 2026
- speech AI
- Real-time Video
- Voice assistants / AI
Description du poste
Overview: Build a real-time multilingual speech platform with live transcription in Darija, French, Arabic and English, natural text‑to‑speech, and a voice assistant that hands off to a human when needed.
Objectives:
- Fine‑tune and evaluate speech recognition for Darija
- Build a low‑latency real‑time audio pipeline
- Design the assistant logic and human handover
Key features:
- Live transcription in Darija, French, Arabic and English
- Natural text‑to‑speech voices
- Voice activity detection for smooth turn‑taking
- Voice assistant for simple requests
- Seamless handover to a human agent
Tech stack: faster‑whisper, Piper / XTTS, Silero VAD, LiveKit
Required application documents: Attach your CV (PDF). Optionally include a short cover letter, your GitHub/portfolio link and your university internship agreement.
Selection process: 1) Email application with the correct project code 2) Profile review 3) Technical interview with the project supervisor 4) Final answer and start.