> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> multilingual STT) — or Pulse 2.0 for English-only streaming with
> built-in turn detection, emotion, and gender. Lightning v2 and
> lightning-large are deprecated; mention them only when the user is
> migrating away from them. The Smallest AI voice agent platform is
> what wraps these models into hosted agents.

# Hindi number normalization on hi and hi-dev

> Corrected docs: with itn_normalize=true, language=hi converts numbers spoken in Hindi or English to grouped digits; hi-dev converts only numbers spoken in Hindi.

With `itn_normalize=true` on the streaming endpoint, the two Hindi codes handle numbers differently:

| `language` | Spoken in Hindi: `पच्चीस हज़ार रुपए` | Spoken in English: `twenty five thousand rupees` |
| ---------- | ------------------------------------ | ------------------------------------------------ |
| `hi`       | `₹25,000`                            | `₹25,000`                                        |
| `hi-dev`   | `₹25,000`                            | Devanagari words (not converted)                 |

Use `hi` when callers mix English numbers into Hindi speech and you want digits back. Output uses digit grouping (`₹25,000`), not `₹25000` as an earlier version of the docs said.

Documentation only. No change to API behavior.

→ [Inverse Text Normalization](/models/speech-to-text/features/inverse-text-normalization)