# Sarvam AI — Introducing Bulbul V4 Flash

- Company: Sarvam AI (sarvam.ai)
- Announced: 2026-09-30T09:00:00+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.sarvam.ai/blogs/bulbul-v4-flash/
- Record: https://forck.live/items/20389-introducing-bulbul-v4-flash
- Subject: Sarvam / Bulbul / Saaras
- Models affected: Bulbul V4 Flash
- Pricing: ₹20 per 10,000 characters (down from ₹30 per 10,000 characters for Bulbul V3)

Sarvam AI released Bulbul V4 Flash, a text-to-speech model trained on over 400 billion audio tokens and distilled for speed and cost. The model achieves under 250 ms time-to-first-audio in production and is priced at ₹20 per 10,000 characters, a third less than the prior V3 model, while offering improved prosody and expressiveness across Indian languages. V4 Flash was pretrained from scratch with a language-balanced curriculum to preserve native accents and speech patterns, including Indian English.

## Evidence

Verbatim from https://www.sarvam.ai/blogs/bulbul-v4-flash/:

> Flash delivers under 250 ms time-to-first-audio in production and costs ₹20 per 10,000 characters.

---

Record: https://forck.live/items/20389-introducing-bulbul-v4-flash
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md