Voice API · India

Text to speech and speech to text API for Hindi and Indian languages.

Hindi, English and ten more Indian languages, with 44 voices each and voice cloning. One API key, plain JSON, and audio back. Stream speech as it is made, transcribe live audio over a WebSocket, manage agents from your code, and receive signed webhooks for every conversation.

Get an API key Read the docs

curl -X POST https://lipivo.com/v1/text-to-speech \
  -H "x-api-key: $LIPIVO_API_KEY" \
  -H "content-type: application/json" \
  -d '{"text": "Hello! Your order arrives tomorrow.", "language_code": "en-IN", "voice_id": "voice:shubh"}' \
  -o reply.mp3

Base URL

https://lipivo.com

Authentication

x-api-key header

Format

JSON in, JSON or audio out

Limits

Per-key spending limits, usage in credits

Quickstart

Your first audio in three steps

1
Get a key
Sign in and create an API key. New workspaces start with free credits.
2
Install an SDK
Python or JavaScript, or call the API with plain HTTP and JSON.
3
Make a request
Send text, get audio back. One header, one JSON body.

pip install lipivo

from lipivo import Lipivo

client = Lipivo(api_key="ind_...")  # or set LIPIVO_API_KEY
speech = client.text_to_speech("Hello! Your order arrives tomorrow.", language_code="en-IN", voice_id="voice:shubh")
open("reply.mp3", "wb").write(speech.audio)
print(speech.credits_remaining)

Both SDKs read LIPIVO_API_KEY from the environment, retry rate limits and network failures, and raise typed errors. SDK reference

What you can build with

The API, piece by piece

Text to speech

44 voices in 12 languages, or a voice you clone with consent. mp3, wav and phone formats.

Reference

Speech to text

Transcribe a recording in its own language, which is found for you, or translate it into English.

Reference

Streaming

Speech that starts playing after one short sentence, and live transcription over a WebSocket.

Reference

Webhooks

Signed events when your agents start a conversation, exchange messages, or credits run low.

Reference

Agents API

Create and change agents, start conversations and calls, and read every transcript from your own code.

Reference

Website widget

Put an agent on your site with one script tag, limited to the origins you allow.

Reference

Speech to text

Transcribe a call recording

Send the audio and get the words and the language back. Leave the language out and it is detected; ask for a translation and you get English.

Reference

curl -X POST https://lipivo.com/v1/speech-to-text \
  -H "x-api-key: $LIPIVO_API_KEY" \
  -H "content-type: application/json" \
  -d "{\"audio_base64\": \"$(base64 -w0 call.wav)\", \"mime_type\": \"audio/wav\"}"

Webhooks

Trust every event you receive

Each event carries a signature made with your endpoint's secret. The SDKs check it, and that it is recent, in one call.

Reference

from lipivo import webhooks

event = webhooks.construct_event(request.body, request.headers["X-Lipivo-Signature"], "whsec_...")

Start building with free credits.

Create a key, set a spending limit on it, and make your first request in a few minutes.

Get an API key Documentation