Skip to main content

Voice Engagements in Customer Journey

Customer Journey fully supports voice engagements. Salted takes the original call recordings from the source platform, provides transcription and imports them together with available metadata. From that moment and on it works directly with the text that is split into individual turns like in any other communication channel.

For audio replay, all recordings associated with an engagement are listed below the engagement start summary. You can play the engagements from within the customer journey if necessary but most customers just continue working with the transcription only.

Supported Languages

Salted supports the following language for voice transcription: Afrikaans, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Cantonese, Catalan, Cebuano, Chichewa, Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Fulah, Galician, Ganda, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kabuverdianu, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latvian, Lingala, Lithuanian, Luo, Luxembourgish, Macedonian, Malay, Malayalam, Maltese, Mandarin Chinese, Māori, Marathi, Mongolian, Nepali, Northern Sotho, Norwegian, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Shona, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tamil, Tajik, Telugu, Thai, Turkish, Ukrainian, Umbundu, Urdu, Uzbek, Vietnamese, Welsh, Wolof, Xhosa, and Zulu.

Speech Transcription Accuracy

Excellent ≤ 5% WER

Bulgarian, Catalan, Czech, Danish, Dutch, English, Finnish, French, Galician, German, Greek, Hindi, Indonesian, Italian, Japanese, Kannada, Malay, Malayalam, Macedonian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Spanish, Swedish, Turkish, Ukrainian and Vietnamese.

High Accuracy >5% to ≤10% WER

Bengali, Belarusian, Bosnian, Cantonese, Estonian, Filipino, Gujarati, Hungarian, Kazakh, Latvian, Lithuanian, Mandarin, Marathi, Nepali, Odia, Persian, Slovenian, Tamil and Telugu.

Good >10% to ≤25% WER

Afrikaans, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Burmese, Cebuano, Croatian, Georgian, Hausa, Hebrew, Icelandic, Javanese, Kabuverdianu, Korean, Kyrgyz, Lingala, Maltese, Mongolian, Māori, Occitan, Punjabi, Sindhi, Swahili, Tajik, Thai, Urdu, Uzbek and Welsh.

Moderate >25% to ≤50% WER

Amharic, Chichewa, Fulah, Ganda, Igbo, Irish, Khmer, Kurdish, Lao, Luxembourgish, Luo, Northern Sotho, Pashto, Shona, Somali, Umbundu, Wolof, Xhosa and Zulu.

Playback of Original Recording

Currently playback of voice recordings are supported only for Amazon Connect. Ingest API does not currently support voice recording.

On platforms on which the voice is not supported in customer journey, you can drill down from the customer journey to the original platform.