Deploy your first Pipecat Cloud agent w/ LMNT TTS
macOS
brew install docker
) only installs the Docker CLI, not the Docker Engine needed to build and run containers.Windows
Create a Docker Hub account
Log in to Docker
No repository creation needed yet
Using uv (recommended)
pip install uv
? Follow the uv installation instructions instead.Using venv (standard)
venv
module:Create a Pipecat Cloud account
Install Pipecat Cloud CLI
pipecatcloud
or pcc
as the command prefix.Authenticate
pcc auth login
to authenticate via your
browser (if this doesn’t work, try python -m pipecatcloud auth login
.)bot.py
: Python entry-point containing your Pipecat agent pipelineDockerfile
: Dockerfile for building the agent containerrequirements.txt
: Python dependencies used by your agent codepcc-deploy.toml
: Pipecat Cloud deployment configuration file (optional)DAILY_API_KEY
can be found at https://pipecat.daily.co under the Settings
in the Daily (WebRTC)
tab.lmnt-agent
with the tag latest
from the current directory.
--platform=linux/arm64
flag is required as Pipecat Cloud runs on
ARM64 architecture.[your-username]/[image-name]:[version-number]
.
env.example
file that you can use as a
template. Create a copy of this file and add your actual API keys:
Alternative: Creating secrets directly via CLI
deploy
command requires three key pieces of information:
pcc-deploy.toml
file that already has the
agent name, image reference, and secret set configured. If you’re using this
file, you can simply run pcc deploy
without additional arguments.See the Deployments section to learn
more.Using credentials for private repositories
--credentials
flag:--min-agents
to 1 or greater will incur charges even when
the agent is not in use.--api-key
flag in future requests.
Next set the key to be used with your agent:
Alternative ways to start a session