Skip to content
SETU by SUPREME AI
Beta

Voice

Text to speech with Nepali and Hindi, and speech to text, on the same key as your models.

Get API key

How it works

  1. 1

    Send text

    Post the words and a language code such as ne, hi or en.

  2. 2

    Get audio back

    Setu returns the audio file in the format you ask for.

  3. 3

    Or the other way

    Send audio to /v1/audio/transcriptions to get text.

Try it

Replace $SETU_API_KEY with a key from the Setu console.

Speak Nepali

curl https://setu.supremeai.services/api/setu/v1/audio/speech \
  -H "Authorization: Bearer $SETU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "input": "नमस्ते! तपाईंलाई कस्तो छ?", "language": "ne", "response_format": "mp3" }' \
  --output hello.mp3

What it does

  • Text to speech with Nepali and Hindi.
  • Speech to text.
  • Read replies aloud in Nepali in your app.
  • Turn voice notes into text.

Limits and status

Beta
  • Needs the audio:speech or audio:transcribe scope.
  • Speech is billed only when audio is produced.
  • Image generation is built but switched off for now.
  • Not yet: Image generation for customers. Built, but switched off by the admin media settings (503 media_disabled).
  • Not yet: Live, two-way voice sessions over the API.
  • Not yet: Video generation.

Status last checked 2026-10-21.

Questions

Is it the same voice as the SUPREME AI app?

Yes. Setu uses the same speech engine as the app’s own voice features.

Start building with Setu

No Setu fee during beta. Create a key and make your first call.

Get API key