Audio Stream
The Audio Stream pipeline is a threaded pipeline that plays audio segments. This pipeline is designed to run on local machines given that it requires access to write to an output device.
Example
The following shows a simple example using this pipeline.
from txtai.pipeline import AudioStream
# Create and run pipeline
audio = AudioStream()
audio(data)
This pipeline may require additional system dependencies. See this section for more.
See the link below for a more detailed example.
Notebook | Description | |
---|---|---|
Speech to Speech RAG ▶️ | Full cycle speech to speech workflow with RAG |
Configuration-driven example
Pipelines are run with Python or configuration. Pipelines can be instantiated in configuration using the lower case name of the pipeline. Configuration-driven pipelines are run with workflows or the API.
config.yml
# Create pipeline using lower case class name
audiostream:
# Run pipeline with workflow
workflow:
audiostream:
tasks:
- action: audiostream
Run with Workflows
from txtai import Application
# Create and run pipeline with workflow
app = Application("config.yml")
list(app.workflow("audiostream", [["numpy data", "sample rate"]]))
Run with API
CONFIG=config.yml uvicorn "txtai.api:app" &
curl \
-X POST "http://localhost:8000/workflow" \
-H "Content-Type: application/json" \
-d '{"name":"audiostream", "elements":[["numpy data", "sample rate"]]}'
Methods
Python documentation for the pipeline.
__init__(rate=None)
Creates an AudioStream pipeline.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
rate
|
optional target sample rate, otherwise uses input target rate with each audio segment |
None
|
Source code in txtai/pipeline/audio/audiostream.py
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
|
__call__(segment)
Queues audio segments for the audio player.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
segment
|
(audio, sample rate)|list |
required |
Returns:
Type | Description |
---|---|
segment |
Source code in txtai/pipeline/audio/audiostream.py
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
|