Models & Languages

Oogam exposes every capability behind a stable model id. Pass the id in the model field of a request (voice, text, or embeddings). Voice and speech pricing also comes back live from GET /voices.

Model catalogue

Voice work uses the naad-* voice models above (see the Audio & Voice reference). naad-text-v1 powers the Text & extraction endpoint, and naad-embed-v1 the embeddings endpoint. sutra-conversation is available on /chat/completions for keys with the Sutra product enabled.

The conversational model

sutra-conversation is the only LLM we publish, and it is ours: it runs on our own GPUs, so nothing you send is resold to a third-party provider. It covers 27 of the 28 languages in-house — Manipuri is currently routed to a cloud model inside the realtime gateway while it is brought in, which is a server-side decision that changes nothing in the API.

It will not state a bill amount, balance, due date, payment status or account status. This is deliberate, not a defect: the model cannot see the caller's account, and when it used to guess it invented figures in 10 of 81 replies — including an impossible “35th of next month”. It now asks for the account number instead. If you need real figures spoken, supply them through a grounded session (set_context or a knowledge base); grounded sessions are exempt from this rule by design.

Replies come back in the caller's native script and run about 15 words. In the realtime pipeline the model also emits a leading (emotion) tag, which the gateway consumes and strips for you. Calling /chat/completions directly, we did not see the tag on plain chat turns — but it is produced under the realtime prompt, so strip a leading (word) tag defensively rather than assuming it is absent.

List models — GET /models

Returns the catalogue in an OpenAI-compatible shape, so standard SDK bootstrap calls work. The live flag tells you which models are actually reachable on this deployment right now — a text or embedding model is live only when its provider is configured.

curl https://platform.oogam.ai/v1/models \
  -H "Authorization: Bearer $OOGAM_API_KEY"

{
  "object": "list",
  "data": [
    { "id": "naad-tts-v1",  "object": "model", "kind": "tts",       "owned_by": "oogam", "live": true },
    { "id": "naad-text-v1", "object": "model", "kind": "chat",      "owned_by": "oogam", "live": true },
    { "id": "naad-embed-v1","object": "model", "kind": "embedding", "owned_by": "oogam", "live": false }
  ]
}

Language codes

All 28 languages are listed below. TTS and STT take a 3-letter code; the realtime WebSocket (Live talk) takes the short code. They match for every language except Indian English, where TTS expects IEN and STT expects ENG. The models never auto-detect — always send the spoken language.