Gnani Text-to-Speech

TTS for 10+ Indian languages with GnaniTTSService (WebSocket), GnaniSSETTSService (SSE), and GnaniHttpTTSService (REST).

Community-maintained integration. This service is built and maintained by Gnani-AI-Mintlify. Pipecat does not test or officially support it. Please report issues and request changes on the source repository. Learn more about community integrations.

​

Overview

GnaniHttpTTSService, GnaniSSETTSService, and GnaniTTSService synthesize speech using Gnani, a production speech AI platform for 10+ Indian languages with real-time streaming and low-latency synthesis.

Use the REST service for simple request/response synthesis, the SSE service for streaming with lower latency than REST, or the WebSocket GnaniTTSService for lowest latency with interruption support via InterruptibleTTSService.

Source Repository

Source code, examples, and issues for the Gnani integration

PyPI Package

The pipecat-gnani package on PyPI

Gnani Website

Learn about Gnani’s speech AI platform

Gnani API Docs

TTS REST, SSE, and WebSocket API reference

Demo Video

Gnani × Pipecat integration — STT/TTS pipeline and interruption handling

gnani-vachana SDK

Core Gnani Python SDK (>= 0.9.0) installed as a dependency

​

Installation

Install the community package directly:

uv add pipecat-gnani

This also installs the gnani-vachana (>= 0.9.0) core SDK. The Python import package name remains gnani.

​

Prerequisites

​

Gnani Account Setup

Before using the Gnani TTS services, you need:

1. Gnani API key: Get one from Gnani APIs.
2. Set credentials: Export GNANI_API_KEY as an environment variable.

​

Required Environment Variables

• GNANI_API_KEY: Your Gnani API key for authentication

​

Configuration

All three services share the same audio-format settings via their Settings dataclasses. The key difference is transport: REST for single-request synthesis, SSE for chunked streaming, and WebSocket for interruptible real-time synthesis.

​

Shared constructor parameters

api_key · str · required

Gnani API key for authentication.

voice_id · str · default: "None"

Voice name for synthesis. Must belong to the selected model. When None, the default is Pranav for timbre-v2.5 and Avinash for timbre-v3.0. See Available voices.

model · str · default: "timbre-v2.5"

TTS model identifier. One of timbre-v2.5 or timbre-v3.0.

sample_rate · int · default: "None"

Output sample rate in Hz. One of 8000, 16000, 22050, 24000, 44100, or 48000. When omitted, negotiated from the pipeline configuration.

settings · Settings · default: "None"

Runtime-updatable TTS settings. See Settings below.

​

GnaniHttpTTSService and GnaniSSETTSService (HTTP)

aiohttp_session · aiohttp.ClientSession · required

Shared aiohttp session for HTTP requests.

​

Settings

Runtime-configurable settings passed via the settings constructor argument using GnaniHttpTTSService.Settings(...), GnaniSSETTSService.Settings(...), or GnaniTTSService.Settings(...).

Parameter	Type	Default	Description
voice	str	None	Voice identifier. Must belong to the selected model. See Available voices.
model	str	"timbre-v2.5"	TTS model (timbre-v2.5 or timbre-v3.0).
language	Language | str	None	Synthesis language: a BCP-47 code such as Language.HI_IN, or "auto". When None, no language is sent.
speed	float	None	Speaking rate from 0.85 to 1.15. When None, the Gnani default (1.0) applies.
encoding	str	"linear_pcm"	Audio encoding. Only linear_pcm is accepted.
container	str	"wav"	Audio container: wav or raw.
sample_width	int	None	Deprecated since 0.6.0. Ignored; output is always 16-bit PCM.
bitrate	str	None	Deprecated since 0.6.0. Ignored; it applies only to MP3 output.

Settings that conflict with the chosen model or fall outside the allowed values raise ValueError when the service is created or updated. Output is always 16-bit PCM, so other encodings and containers (mp3, ogg, mulaw, alaw) are rejected.

Voice, model, language, and speed changes take effect on the next synthesis request. If an update is rejected, the previous settings stay in place. For the supported languages, see the Gnani TTS documentation.

​

Available voices

​

timbre-v2.5 (42 voices)

Language	Voices
Hindi	Nalini, Bhavna, Yashvi, Urmila, Jwala, Chitra, Ambuja, Deepak, Roopesh, Vikrant, Hemraj, Jalaj, Omkar
English	Kaveri, Trupti, Devika, Pranav, Shlok, Girish
Tamil	Asmita, Trisha, Brinda, Vedika, Noopur
Telugu	Suhana, Lehara, Lavanya, Yukti, Varuni
Kannada	Saanvi, Kavin
Malayalam	Reshma, Riyaan
Marathi	Zahira, Ishaan
Bengali	Kirra, Dhruva
Gujarati	Falak, Veera
Punjabi	Mehuli, Zayan
Hinglish	Poorvi

​

timbre-v3.0 (13 voices)

Avinash, Chetana, Devansh, Harshad, Kalpana, Lakshmi, Prakash, Riyaa, Shivani, Shubham, Tarika, Vasudha, Yashraj

The voice lists are also available in code as pipecat_gnani.TIMBRE_V25_VOICES and pipecat_gnani.TIMBRE_V30_VOICES.

​

Usage

​

Streaming with interruption (WebSocket)

import os

from pipecat_gnani import GnaniTTSService

tts = GnaniTTSService(
    api_key=os.getenv("GNANI_API_KEY"),
    sample_rate=16000,
    settings=GnaniTTSService.Settings(
        voice="Pranav",
    ),
)

# ... add tts to your pipeline

​

Choosing a model, language, and speed

import os

from pipecat.transcriptions.language import Language
from pipecat_gnani import GnaniTTSService

tts = GnaniTTSService(
    api_key=os.getenv("GNANI_API_KEY"),
    sample_rate=16000,
    settings=GnaniTTSService.Settings(
        model="timbre-v3.0",
        voice="Shivani",
        language=Language.HI_IN,
        speed=1.1,
    ),
)

# ... add tts to your pipeline

​

SSE streaming

import os

from pipecat_gnani import GnaniSSETTSService

tts = GnaniSSETTSService(
    api_key=os.getenv("GNANI_API_KEY"),
    aiohttp_session=session,
    settings=GnaniSSETTSService.Settings(
        voice="Pranav",
    ),
)

# ... add tts to your pipeline

​

REST (non-streaming)

import os

from pipecat_gnani import GnaniHttpTTSService

tts = GnaniHttpTTSService(
    api_key=os.getenv("GNANI_API_KEY"),
    aiohttp_session=session,
    settings=GnaniHttpTTSService.Settings(
        voice="Pranav",
    ),
)

# ... add tts to your pipeline

​

Minimal pipeline example

import os

from pipecat.pipeline.pipeline import Pipeline
from pipecat.transcriptions.language import Language
from pipecat_gnani import GnaniSTTService, GnaniTTSService

stt = GnaniSTTService(
    api_key=os.getenv("GNANI_API_KEY"),
    settings=GnaniSTTService.Settings(language=Language.HI_IN),
)

tts = GnaniTTSService(
    api_key=os.getenv("GNANI_API_KEY"),
    settings=GnaniTTSService.Settings(voice="Pranav"),
)

pipeline = Pipeline(
    [
        transport.input(),
        stt,
        # ... LLM and aggregators
        tts,
        transport.output(),
    ]
)

​

Compatibility

Tested with the latest Pipecat main branch (v1.5.0+) using pipecat-gnani. Requires gnani-vachana >= 0.9.0. Check the source repository for the latest tested version and changelog.