Synthetic Voices

One hundred and ninety five voices carry the conversational tag, 84 percent of the catalog. Streaming is what makes them feel live: audio begins playing before the sentence has finished rendering.

Narration is the one job where a voice has to hold up for hours rather than seconds. 163 of the 244 voices here carry the narration tag, the largest group in the catalog, across English, Hindi and nine other Indic languages.

Seventy two voices cover eleven Indic languages plus English, so one voice serves a Hindi caller and a Tamil caller without re-casting. Hindi and English can alternate inside a single sentence.

At volume the cost driver is duplication, not generation. Hashing text and skipping what already exists removes most of it, since catalog and template work repeats the same phrases constantly.

Voice agents live or die on the pause before a reply. Synthesis starts in about 200 milliseconds and runs at 3.3 times real time, which leaves the budget where it usually belongs: your model.

One hundred and twenty male voices across every accent group and all twelve recommended languages. Most carry an Indic recommendation, which is unusual in catalogs that treat Indian languages as an afterthought.

One hundred and four voices carry an Indian accent, more than twice any other group. They handle English words inside Devanagari sentences without changing register, which is how Indian English is actually spoken.

Corporate narration needs consistent terminology more than it needs a particular tone. Pronunciation dictionaries fix brand and product names once, so every module in a library matches the first one.

Generation runs at 3.3 times real time, so audio renders faster than it plays and the buffer stays ahead. First audio arrives in about 200 milliseconds over SSE or WebSocket.

One hundred and one female voices, spanning six accent groups and all twelve recommended languages. At that scale accent and language usually constrain casting more than gender does.