Sometimes a Unicode character such as a smart quote, an em dash (—), or Unicode white space slips into your carefully crafted 125-character message, and your message gets segmented and priced at two messages instead of one.
When Unicode characters are used in an SMS message, they must be encoded using the UCS-2 character set. UCS-2 characters take 16 bits to encode instead of the seven bits used by the GSM character set used for most common letters and symbols, so when a message includes any Unicode character, it's segmented at 70 characters instead of 160 characters per message segment.
Plivo's intelligent message encoding feature detects easy-to-miss Unicode characters and replaces them with similar GSM-encoded characters to ensure that your message gets segmented at 160 characters and save you from sending two messages.
Messages that include emoji or language-based characters such as kanji are not transliterated with automatic encoding. Here's the list of Unicode character sets replaced by automatic encoding.