Skip to content
SETU by SUPREME AI

Setu for Voice apps

Speech in and speech out, on the same key as your models.

Get API key

The problem

A voice feature needs speech to text, a model and text to speech, usually from three different providers.

What you can do

  • Turn a voice note into text, answer it with a model, and read the answer aloud.
  • Read replies aloud in Nepali, Hindi or English.
  • Add voice input to a form or a support chat.

The parts you use

  • Voice

    Beta

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

    Learn more about Voice

  • Models API

    Beta

    OpenAI-compatible chat completions with streaming and tool calls. Point your OpenAI client at Setu and keep your code.

    Learn more about Models API

Speak Nepali

Replace $SETU_API_KEY with a key from the Setu console.

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

You stay in control

Speech is charged only when audio is produced. Live two-way voice sessions over the API are not offered yet.

What it costs

No Setu fee during beta. Calls use the credits in your SUPREME AI account.

Get API keySee pricing

Start building with Setu

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

Get API key