Oogam Documentation
One API for Indian-language voice: Text to Speech, Speech to Text and realtime Live talk over a WebSocket — 27 Indian languages and English, one key, rupee billing.
Everything is on v2. Send naad-tts-v2, naad-stt-v2 and naad-sts-v2; existing -v1 integrations remain supported. See the model catalogue.
curl https://platform.oogam.ai/v1/audio/speech \
-H "Authorization: Bearer $OOGAM_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"naad-tts-v2","input":"नमस्ते!","voice":"aditi","language":"HIN"}' \
--output namaste.wavBefore you integrate
Check your account's enabled products and model availability. Transcription is synchronous — async job mode is off. Multi-speaker conversation, batch speech-to-speech and audio translation do not work today, and creating, calibrating or deleting voice clones is blocked (existing clones still synthesise). Read the audio availability notes before choosing an endpoint.
| Endpoint | Does |
|---|---|
POST /audio/speech | Text to Speech — text in, audio out |
POST /audio/transcriptions | Speech to Text — audio in, transcript out (currently synchronous) |
POST /chat/completions | Text & extraction — OpenAI-compatible, JSON-mode enforced |
POST /kb | Knowledge bases — host documents, ground live calls |
GET /models | Model catalog — the ids you can send |
GET /voices | Voices & models with availability and live pricing |
WS /realtime | Live conversation — mic in, agent voice out |
REST base https://platform.oogam.ai/v1 · realtime wss://platform.oogam.ai/v1/realtime · auth Authorization: Bearer sk-setu-…