Select the Model and voice

• Models & Voice section decide karta hai ki aapka voice agent conversations mein kaise sunega, sochega aur bolega.

• Sabse pehle Pipeline Mode choose karein:

  • STT + LLM + TTS pipeline aapko zyada control deta hai kyunki speech-to-text, AI brain aur text-to-speech alag-alag configure hote hain.

  • Realtime model ek single unified setup deta hai jo faster configuration ke liye useful hai.

• TTS (Text-to-Speech) decide karta hai agent ki voice kaisi hogi — aisa voice model select karein jo aapke brand aur audience se match kare.

• LLM (Large Language Model) agent ka brain hota hai — yeh response quality, speed aur instruction follow karne ki ability control karta hai. Model choose karte waqt speed, cost aur complexity ka dhyan rakhein.

• STT (Speech-to-Text) user ki voice ko text mein convert karta hai — better understanding ke liye high-accuracy model aur correct language select karein.

• Noise Cancellation enable karein taaki background noise remove ho aur calls noisy environment mein bhi clear rahein.

• Pipeline mode, models, voice aur noise settings ko sahi configure karne se aapka voice agent natural, intelligent aur professional sound karega.