Scale your calls globally with the ability to speak text to callers in multiple languages and accents.
Split/Multitrack Recording (Beta)
Record up to 32 call participants in separate tracks to enable more accurate call transcription, content search, sentiment analysis and more.
Speech Synthesis Markup Language (SSML)
Programmatically control the pronunciation of text, including punctuation, pausing, emphasis, volume, pitch, rate of speech, phonetic pronunciation and context disambiguation.