pipecat-blynt 0.1.0

Blynt STT plugin for Pipecat - Real-time speech recognition with Blynt API

Pipecat Plugin - Blynt STT

Blynt Speech-to-Text plugin for Pipecat, providing real-time speech recognition through Blynt's ASR API.

Features

• Real-time streaming speech recognition
• Support for interim and final transcriptions
• Deployment-scoped, Bearer-authenticated WebSocket connection to the Blynt API

Installation

# Using pip
pip install pipecat-blynt

# Using uv
uv add pipecat-blynt

Usage

The plugin connects to a Blynt deployment, so you must supply a deployment_id and an API key. Both can be passed directly or via the BLYNT_DEPLOYMENT_ID and BLYNT_API_KEY environment variables.

from pipecat_blynt import BlyntSTTService, BlyntSTTOptions, STTLanguages

# Create STT service with configuration
stt = BlyntSTTService(
    options=BlyntSTTOptions(
        deployment_id="680989...",  # or set BLYNT_DEPLOYMENT_ID
        api_key="sk-..."  # or set BLYNT_API_KEY
    ),
)

# Or, with both read from the environment:
stt = BlyntSTTService(options=BlyntSTTOptions())

# Use in your Pipecat pipeline
# ... add to pipeline as usual

Turns are delimited from the pipeline's VADUserStartedSpeakingFrame / VADUserStartedSpeakingFrame, so a VAD (e.g. Silero) must run upstream in the pipeline.

Note: given the ASR processes audio in between VADUserStartedSpeakingFrame and VADUserStoppedSpeakingFrame, it is recommended to use a VAD with a stop_secs of at least 0.5s to avoid splitting the utterance into multiple Blynt decodes.

Configuration Options

BlyntSTTOptions

• deployment_id (optional): Blynt deployment id to run the session against. Falls back to the BLYNT_DEPLOYMENT_ID environment variable
• api_key (optional): Blynt API key for Bearer auth. Falls back to the BLYNT_API_KEY environment variable

Requirements

• Python >= 3.12
• pipecat-ai >= 0.0.96
• websockets >= 14.0
• loguru >= 0.7.0

License

Same as Pipecat (BSD 2-Clause License)