Kenpath Labs

Quickstart

Create a key, make a request, and stream the response.

Get an API key

Create a key in the console under API keys. Keys look like sk_live_… and are shown once at creation; store them in a secret manager or environment variable, never in client code or version control.

export SVARA_API_KEY="sk_live_..."

Make your first request

The svara-voice SDK is the shortest path. If you already use the OpenAI SDK, point it at the Svara base URL instead — the request shape is the same:

pip install svara-voice
from svara import Svara


client = Svara()                          # reads SVARA_API_KEY
audio = client.speech.create(
    input="नमस्ते! Welcome to Svara.",
    voice="sv_enhdbrj5",                  # Aanya
    response_format="mp3",
)
open("hello.mp3", "wb").write(audio)

Stream it

Set stream: true and consume chunks as they arrive; with pcmoutput first audio arrives in ~80 ms rather than after the whole clip is generated. If the text comes from an LLM, use the WebSocket input-streaming API instead — it accepts text while the model is still writing, so synthesis doesn’t wait for a complete sentence:

from svara import Svara


client = Svara()
for chunk in client.speech.stream(
    input="This sentence starts playing before it finishes generating.",
    voice="sv_enhdbrj5",            # Aanya
    response_format="pcm",          # 24 kHz, 16-bit LE, mono
):
    player.feed(chunk)              # your audio sink


# from an LLM? one WebSocket, speech before the sentence ends:
#   async for audio in AsyncSvara().speech.stream_input(deltas(), voice="sv_enhdbrj5"): ...

Format choices, playback, and telephony output are on the Streaming page.

Explore voices and languages

These endpoints are public, no key required:

  • GET /v1/voices: the current voice roster, each with a preview_url
  • GET /v1/languages: all 82 supported languages, for building pickers
  • GET /v1/models: available models

Building with a coding agent? Install the Svara agent skills.

The console playground runs the same API from the browser: try voices, languages, and multi-speaker scenes without writing code.