What is TTS (text-to-speech)?
Also called: speech synthesis
TTS, or text-to-speech, is the step that turns the agent's written reply into audible speech.
Modern systems produce natural prosody, but the hard parts in India are ordinary: saying a rupee amount, a rank, a percentage or a date the way a local speaker would rather than digit by digit.
Why it matters for Indian calling. A voice that mispronounces amounts and place names is worse than a plain one, because it signals the call is from somewhere else.
Related terms, in one line each
- Voice cloning
- Voice cloning is creating a synthetic copy of a specific person's voice from recordings of them speaking.
- Dialect
- A dialect is a regional variety of a language with its own vocabulary, pronunciation and grammar, distinct enough that speakers immediately recognise where a person is from.
- ASR (speech recognition)
- ASR, or automatic speech recognition, is the step that converts the caller's spoken audio into text the system can act on.
Where TTS (text-to-speech) comes up next
- AI voice agent
- In India the deciding factor is rarely fluency. It is whether the agent handles a caller who switches language mid-sentence and speaks a regional variety rather than textbook Telugu or Hindi.
More in the AI behind the call