Real-time interpreting of voice calls with parties speaking different languages

In this demo with 1-to-1 voice calls, both parties hear each other’s voice and the corresponding real-time speech translations. Optionally, speech transcripts and translation texts may be shown in a display application like within the Vonage Contact Center (VCC) agent console.

Two parties speaking different languages using their own phones are connected via the Vonage Communications Platform (VCP) using the Vonage API services and partner AI services to talk to each other and also hear the real-time interpretation of their spoken phrases. 

A customer and a call center agent speaking different languages are connected via the Vonage Communications Platform (VCP) using the Vonage Contact Center (VCC), Vonage API services,  and partner AI services to talk to each other and also hear the real-time interpretation of their spoken phrases.

A Vonage Business Communications (VBC) user and an external party speaking different languages are connected via the Vonage Communications Platform (VCP) using the VBC services, Vonage API services, and partner AI services to talk to each other and also hear the real-time interpretation of their spoken phrases.

Advantages of the patent-pending real-time speech interpreting solutions for voice and video calls from Vonage

It will be available across all Vonage products including Vonage Voice APIs, Vonage Video APIs, Vonage Contact Center services, and Vonage Business Communications services.

No special equipment is needed for the participants in the voice or video calls, they keep using their existing devices.

There is no need to press buttons while speaking or to start/stop speaking.

In this early preview version, it supports:
48 languages locales,
37 main languages.

The 48 language locales are:
  • "1": "عربي (Arabic)",
  • "2": "Euskara (Basque)",
  • "3": "বাংলা (Bengali)",
  • "4": "Català - Valencià (Catalan)",
  • "5": "广东话 (Chinese - Cantonese)",
  • "6": "普通话 (Chinese - Mandarin)",
  • "7": "台湾普通话 (Chinese - Mandarin - Taiwan)",
  • "8": "Čeština (Czech)",
  • "9": "Dansk (Danish)",
  • "10": "Nederlands (Dutch)",
  • "11": "English - Australia",
  • "12": "English - India",
  • "13": "English - South Africa",
  • "14": "English - United Kingdom",
  • "15": "English - United States",
  • "16": "English - Wales",
  • "17": "Filipino",
  • "18": "Suomalainen (Finnish)",
  • "19": "Français - Canada (French)",
  • "20": "Français - France (French)",
  • "21": "Deutsch (German)",
  • "22": "Ελληνικά (Greek)",
  • "23": "עִברִית (Hebrew)",
  • "24": "हिंदी (Hindi)",
  • "25": "Magyar (Hungarian)",
  • "26": "Íslensku (Icelandic)",
  • "27": "Bahasa Indonesia (Indonesian)",
  • "28": "Italiano (Italian)",
  • "29": "日本 (Japanese)",
  • "30": "한국인 (Korean)",
  • "31": "മലയാളം (Malayalam)",
  • "32": "Norsk (Norwegian)",
  • "33": "Polskie (Polish)",
  • "34": "Português - Brasil (Portuguese)",
  • "35": "Português - Portugal (Portuguese)",
  • "36": "Română (Romanian)",
  • "37": "Pусский (Russian)",
  • "38": "Slovenský (Slovak)",
  • "39": "Español - México (Spanish)",
  • "40": "Español - España (Spanish)",
  • "41": "Español - Estados Unidos (Spanish)",
  • "42": "Svenska (Swedish)",
  • "43": "தமிழ் (Tamil)",
  • "44": "తెలుగు (Telugu)",
  • "45": "ไทย (Thai)",
  • "46": "Türk (Turkish)",
  • "47": "Українська (Ukrainian)",
  • "48": "Tiếng Việt (Vietnamese)",
The 37 main languages are:
  • "Arabic",
  • "Basque",
  • "Bengali",
  • "Catalan",
  • "Chinese",
  • "Czech",
  • "Danish",
  • "Dutch",
  • "English",
  • "Filipino",
  • "Finnish",
  • "French",
  • "German",
  • "Greek",
  • "Hebrew",
  • "Hindi",
  • "Hungarian",
  • "Icelandic",
  • "Indonesian",
  • "Italian",
  • "Japanese",
  • "Korean",
  • "Malayalam",
  • "Norwegian",
  • "Polish",
  • "Portuguese",
  • "Romanian",
  • "Russian",
  • "Slovak",
  • "Spanish",
  • "Swedish",
  • "Tamil",
  • "Telugu",
  • "Thai",
  • "Turkish",
  • "Ukrainian",
  • "Vietnamese",