Sarvam launches Bulbul V4 Flash for Indian languages
Bulbul V4 Flash is a fast text-to-speech model with 83 voices across 11 Indian languages. It reaches first audio in under 250 ms and costs ₹20 per 10,000 characters.
What it does
Bulbul V4 Flash is Sarvam's text-to-speech model for Indian languages, built for real-time use. It aims to capture emotion, emphasis and pacing in each language.
It launches with 83 voices across 11 languages and 224 voice-and-style combinations, for uses from customer care to narration.
Results and limits
Sarvam reports under 250 ms time-to-first-audio in production. The source gives no independent quality tests.
Worth knowing
It costs ₹20 per 10,000 characters. Existing Bulbul users can switch through the same Bulbul API.
Try it yourself
Pick a [Hindi/Tamil/other] voice and a narration style, then enter: "[Two-sentence voiceover script in that language]". Compare two voices for the same line.