Cartesia Voice Agents SDK
Project description
Cartesia Line SDK
Build intelligent, low-latency voice agents with background reasoning.
With Line you can,
- Create your first voice agent from scratch, deploy, and talk to it in under 5 minutes.
- Turn any existing chatbot or text agent you've already built into a low-latency voice agent.
- Spin up common use cases for support or scheduling from ready-made templates.
- Deploy production-ready systems with auto-scaling, telephony integration, metrics, and call analytics.
Why Line?
- 🔗 Event-driven design to easily define multi-agent architectures with powerful background reasoning.
- ⚡ State-of-the-art voice models using Sonic TTS and Ink STT deliver the lowest latency voice experience.
- 📋 Pre-built templates for common use cases like customer support, sales agents, form filling, and more.
- 🔌 Easy integrations with tools, MCPs, and other frameworks out of the box.
- 🤝 Support for handoffs between agents and humans.
- 🧠 Reasoning agnostic works with any LLM, text agent, or chatbot code.
- 🚀 Instant deployment so you can build, deploy, and start talking in minutes with no infrastructure setup.
Quickstart (< 5 minutes)
The Line SDK is designed to be used with the Cartesia's voice agent platform Line.
- Create a Cartesia account.
- Follow the quickstart guide.
And you'll be able to make your first voice call in a few minutes.
Install the SDK
pip install cartesia-line
Common Use Cases
| Use Case | Example |
|---|---|
| Basic chat | examples/basic_chat/ |
| Form filling | examples/form-filling/ |
| Background reasoning | examples/sales_with_leads/ |
| Support | examples/personal_banking_handoffs/ |
Going Deeper
-
More examples: examples/ - See all available examples and patterns
-
3rd party integrations: example_integrations/ - See example integrations for external services
[!NOTE] While Cartesia approves each example, they are implemented and maintained by our partners.
-
Full API reference: docs.cartesia.ai/line
-
Get help: Discord community
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cartesia_line-0.1.7.tar.gz.
File metadata
- Download URL: cartesia_line-0.1.7.tar.gz
- Upload date:
- Size: 61.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c01d7171eb2d3d9a3abbeda259c4b67cf1d8b2358698e00a2ff0023d74c5c0b2
|
|
| MD5 |
1002a8e09a1e86426e7ba9dc49a475a5
|
|
| BLAKE2b-256 |
6423c501be979f01bae97110bcfeb4e273f5d54ec62450241a84955506523ded
|
Provenance
The following attestation bundles were made for cartesia_line-0.1.7.tar.gz:
Publisher:
publish-to-pypi.yaml on cartesia-ai/line
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
cartesia_line-0.1.7.tar.gz -
Subject digest:
c01d7171eb2d3d9a3abbeda259c4b67cf1d8b2358698e00a2ff0023d74c5c0b2 - Sigstore transparency entry: 766067131
- Sigstore integration time:
-
Permalink:
cartesia-ai/line@b64f468d1b4f81b48500df7a135871ee7fea92bf -
Branch / Tag:
refs/heads/main - Owner: https://github.com/cartesia-ai
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-to-pypi.yaml@b64f468d1b4f81b48500df7a135871ee7fea92bf -
Trigger Event:
workflow_run
-
Statement type:
File details
Details for the file cartesia_line-0.1.7-py3-none-any.whl.
File metadata
- Download URL: cartesia_line-0.1.7-py3-none-any.whl
- Upload date:
- Size: 58.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b66fdec6cc248046a39286664bfb365b1462fc93345ea11dfaf09a058fca2cc
|
|
| MD5 |
c832e3b279984750bae1650b59e3e1bc
|
|
| BLAKE2b-256 |
0e33105739f358a9736f8291c0ca5880a53b23859d8895bb4fa0dabafa2149c5
|
Provenance
The following attestation bundles were made for cartesia_line-0.1.7-py3-none-any.whl:
Publisher:
publish-to-pypi.yaml on cartesia-ai/line
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
cartesia_line-0.1.7-py3-none-any.whl -
Subject digest:
4b66fdec6cc248046a39286664bfb365b1462fc93345ea11dfaf09a058fca2cc - Sigstore transparency entry: 766067135
- Sigstore integration time:
-
Permalink:
cartesia-ai/line@b64f468d1b4f81b48500df7a135871ee7fea92bf -
Branch / Tag:
refs/heads/main - Owner: https://github.com/cartesia-ai
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-to-pypi.yaml@b64f468d1b4f81b48500df7a135871ee7fea92bf -
Trigger Event:
workflow_run
-
Statement type: