Skip to main content

AwaazAI WebSocket frame serializer for Pipecat for hosting agents on telephony

Project description

Pipecat Awaaz AI Telephony Serializer Integration

Host your Pipecat agents with Awaaz AI telephony stack.

Maintainer: Awaaz AI

Installation

pip install pipecat-awaazai

Or via uv, update your pyproject.toml:

[project]
name = "your-project"
version = "0.1.0"
dependencies = [
    "pipecat-awaazai",
    "another-package"
]
uv sync

Prerequisites

  • Purchase a Phone number from Awaaz AI

Usage with Pipecat Pipeline

AwaazAIFrameSerializer convert between frames and media streams, enabling real-time communication over a websocket to host agent over Awaaz AI's telephony stack over an indian phone number

from pipecat_awaazai import AwaazAIFrameSerializer

    transport = FastAPIWebsocketTransport(
        websocket=websocket_client,
        params=FastAPIWebsocketParams(
            audio_out_enabled=True,
            add_wav_header=True,
            vad_enabled=True,
            vad_analyzer=SileroVADAnalyzer(sample_rate=8000),
            vad_audio_passthrough=True,
            serializer=AwaazAIFrameSerializer(stream_id),
            audio_out_sample_rate=8000
        ),
    )

See example.py for a complete working example including event handlers and transport setup.

Running the Example

  1. Start ngrok: In a new terminal, start ngrok to tunnel the local server:

    ngrok http 7860
    
  2. Share your ngrok endpoint url (e.g. https://foo.bar.ngrok-free.dev) with us at https://www.awaaz.ai/#Book-Demo; you'll get an email with a demo phone number

  3. Install dependencies:

    uv sync
    
  4. Set up your environment

    cp env.example .env
    
  5. Run:

    uv run bot.py --transport awaazai --proxy your_ngrok_url
    

The bot will create a websocket that will accept connections from Awaaz AI assigned phone number. Once websocket is running, call Awaaz AI assigned phone number and you will be able to interact over the call

Compatibility

Tested with Pipecat v0.0.101

  • Python 3.10+

License

BSD-2-Clause - see LICENSE

Support

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pipecat_awaazai-0.1.1.tar.gz (3.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pipecat_awaazai-0.1.1-py3-none-any.whl (4.4 kB view details)

Uploaded Python 3

File details

Details for the file pipecat_awaazai-0.1.1.tar.gz.

File metadata

  • Download URL: pipecat_awaazai-0.1.1.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for pipecat_awaazai-0.1.1.tar.gz
Algorithm Hash digest
SHA256 f19fabd2605e3a5201428b69e96c80a026f5388d5825f24856423c39bc118452
MD5 19974ba9dafb9504d7a8593a44c85fd7
BLAKE2b-256 7320c025d3c409abfbf1b7f3484781650f90592fec1596eb8d71e6e000c60cf6

See more details on using hashes here.

File details

Details for the file pipecat_awaazai-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: pipecat_awaazai-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 4.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for pipecat_awaazai-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1e7c17eb776ae6f2f0de0fe364572423db173475e884f3678488774eb9015c97
MD5 66108e25c1e00355ed47eaa9b4a30b6d
BLAKE2b-256 0104274924e2ea57c6204dc0c82b69bac5fbf119aa7143e927ad97a79c8a988d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page