Skip to main content

​
Overview

SimplismartHttpTTSService generates speech from text using the Simplismart streaming /tts API. Audio is returned as raw PCM (s16le, mono) at 24 kHz, suitable for real-time voice pipelines.

Source Repository

Source code, examples, and issues for the Simplismart integration

Simplismart

Learn more about Simplismart and its AI services

​
Installation

This is a community-maintained package distributed separately from pipecat-ai. It is not published to PyPI, so install it from source: 
uv pip install git+https://github.com/simpli-smart/pipecat-simplismart.git

​
Prerequisites

​
Simplismart Account Setup

Before using the Simplismart text-to-speech service, you need a Simplismart account and API key. See Simplismart to get started.

​
Required Environment Variables

  • SIMPLISMART_API_KEY: Bearer token used to authenticate TTS requests. Can be passed directly via the api_key constructor argument instead.
  • SIMPLISMART_TTS_URL: TTS endpoint URL. Defaults to https://api.simplismart.live/tts if not set.

​
Configuration

​
api_key
str
default:"None"
Simplismart bearer token. Falls back to the SIMPLISMART_API_KEY environment variable if not provided.
​
base_url
str
default:"None"
TTS endpoint URL (e.g. https://api.simplismart.live/tts). Falls back to the SIMPLISMART_TTS_URL environment variable, then to https://api.simplismart.live/tts.
​
aiohttp_session
aiohttp.ClientSession
default:"None"
Optional shared HTTP client session. If not provided, the service creates and manages its own session.
​
sample_rate
int
default:"None"
Output sample rate. Should match SimplismartHttpTTSService.SAMPLE_RATE (24000) for correct playback.
​
settings
SimplismartHttpTTSService.Settings
default:"None"
Voice, model, and generation settings. See Settings below.

​
Settings

Runtime-configurable settings passed via the settings constructor argument using SimplismartHttpTTSService.Settings(...).
ParameterTypeDefaultDescription
modelstr"canopylabs/orpheus-3b-0.1-ft"Simplismart TTS model identifier.
voicestr"tara"Voice used for speech generation.
temperaturefloat0.7Sampling temperature for speech generation.
top_pfloat0.9Top-p nucleus sampling.
repetition_penaltyfloat1.5Repetition penalty.
max_tokensint1000Max new tokens for the TTS model.
Available parameters and defaults are defined by the integration. See the source repository for the authoritative, up-to-date list.

​
Usage

from pipecat_simplismart import SimplismartHttpTTSService

tts = SimplismartHttpTTSService(
    api_key="YOUR_KEY",
    base_url="https://api.simplismart.live/tts",
    sample_rate=SimplismartHttpTTSService.SAMPLE_RATE,
    settings=SimplismartHttpTTSService.Settings(
        model="canopylabs/orpheus-3b-0.1-ft",
        voice="tara",
    ),
)

# ... add tts to your pipeline.

​
Compatibility

Tested with Pipecat v1.1.0 (pipecat-ai>=0.0.86). Check the source repository for the latest tested version and changelog.