Skip to main content
POST
/
api
/
v1
/
tts
/
inference
TTS Inference
curl --request POST \
  --url https://api.vachana.ai/api/v1/tts/inference \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key-ID: <x-api-key-id>' \
  --data '
{
  "audio_config": {
    "bitrate": "192k",
    "container": "mp3",
    "encoding": "linear_pcm",
    "num_channels": 1,
    "sample_rate": 44100,
    "sample_width": 2
  },
  "model": "vachana-voice-v3",
  "text": "नमस्ते, आप कैसे हैं?"
}
'
"<string>"
Currently in beta. You’re on the priority waitlist and among the first to get access.

​
Overview

Get the complete synthesized audio in one response. Best for downloads or batch processing. For streaming playback, see TTS Streaming or TTS Realtime.
Passing numbers, IDs, dates, or currency as raw strings causes mispronunciations. See the Input Formatting Guide for correct formatting of phone numbers, account numbers, PINs, Aadhaar, vehicle registration numbers, GSTIN, currency, and more.

​
Available Voices

VoiceGenderDescription
KaranMaleBold, Trustworthy
SimranFemaleConfident, Bright
NaraFemaleGentle, Expressive
RiyaFemaleCheerful, Energetic
VirajMaleCommanding, Dynamic
RajuMaleGrounded, Conversational

​
Python SDK

The official Python SDK lets you synthesize speech in one line, without constructing JSON payloads or handling binary audio responses manually.

​
Installation

pip install gnani-vachana
Requires Python 3.9+.

​
Authentication

The TTS client requires only your API key. 
from gnani.tts import GnaniTTSClient

client = GnaniTTSClient(api_key="your-api-key")

​
Synthesize Speech

The synthesize method returns the complete audio as bytes, which you can write to a file or pass directly to an audio player. 
from gnani.tts import GnaniTTSClient

client = GnaniTTSClient(api_key="your-api-key")

audio = client.synthesize(
    "नमस्ते, आप कैसे हैं?",
    voice="sia",
)

with open("output.wav", "wb") as f:
    f.write(audio)

​
Custom Audio Config

Control the sample rate, encoding, and container format of the output audio. 
from gnani.tts import GnaniTTSClient, AudioConfig

client = GnaniTTSClient(api_key="your-api-key")

audio = client.synthesize(
    "यह एक टेस्ट है",
    voice="raju",
    audio_config=AudioConfig(
        sample_rate=44100,
        encoding="linear_pcm",
        container="wav",
    ),
)

with open("output.wav", "wb") as f:
    f.write(audio)

​
List Available Voices

from gnani.tts import GnaniTTSClient

voices = GnaniTTSClient.supported_voices()
print(voices)

​
Supported Languages

The Vachana API supports 2 languages.
LanguageNative ScriptExample
EnglishLatin”I am going to the market”
HindiDevanagari (हिन्दी)“मैं बाज़ार जा रहा हूँ”

Headers

​
X-API-Key-ID
string
required

Body

application/json

Request body for TTS inference.

​
text
string
required
​
model
enum<string>
required

Supported TTS models.

Available options:
vachana-voice-v3
​
audio_config
AudioConfig · object
required

Audio output configuration.

​
voice
enum<string>

ID of a pre-defined voice. Ignored if speaker_embedding is provided.

Available options:
Karan,
Simran,
Nara,
Riya,
Viraj,
Raju

Response

Successful audio synthesis

The response is of type file.