Cartesia
Cartesia is a service that provides Speech-to-Text (STT) and Text-to-Speech (TTS) capabilities. It's designed for real-time voice applications, making it ideal for voice AI agents, transcription pipelines, and conversational interfaces.
The Cartesia plugin for the Stream Python AI SDK allows you to add STT and TTS functionality to your project.
Installation
Install the Stream Cartesia plugin with
uv add "vision-agents[cartesia]"
# or directly
uv add vision-agents-plugins-cartesia
Examples
Read on for some key details and check out our Cartesia examples to see working code samples:
- in main.py we see a voice bot that uses Cartesia STT and TTS in a Stream call
- in narrator-example.py we see a well-prompted combination of an STT -> LLM -> TTS flow that leverages Cartesia's Ink and Sonic models to narrate a creative story from the user's input
Initialisation
The Cartesia plugin for Stream exposes STT and TTS classes:
from vision_agents.plugins import cartesia
stt = cartesia.STT()
tts = cartesia.TTS()
To initialise without passing in the API key, make sure the `CARTESIA_API_KEY` is available as an environment variable.
You can do this either by defining it in a `.env` file or exporting it directly in your terminal.
Parameters
These are the parameters available in the Cartesia STT plugin for you to customise:
| Name | Type | Default | Description |
|---|---|---|---|
api_key |
str or None |
None |
Your Cartesia API key. If not provided, the plugin will look for the CARTESIA_API_KEY environment variable. |
model |
str |
"ink-2" |
ID of the Cartesia STT model to use. |
sample_rate |
int |
16000 |
Sample rate (in Hz) sent to Cartesia. |
encoding |
str |
"pcm_s16le" |
PCM encoding sent to Cartesia. |
cartesia_version |
str |
"2026-03-01" |
Cartesia API version used for the turn-detection websocket. |
These are the parameters available in the Cartesia TTS plugin for you to customise:
| Name | Type | Default | Description |
|---|---|---|---|
api_key |
str or None |
None |
Your Cartesia API key. If not provided, the plugin will look for the CARTESIA_API_KEY environment variable. |
model_id |
str |
"sonic-3.5" |
ID of the Cartesia TTS model to use. |
voice_id |
str or None |
"f9836c6e-a0bd-460e-9d3c-f7299fa60f94" |
ID of the voice to use for TTS responses. |
sample_rate |
int |
16000 |
Sample rate (in Hz) used for audio processing. |
Functionality
Send audio to transcribe speech
STT streams PCM audio to Cartesia Ink and emits transcript and turn events that Vision Agents can use for interruption and eager turn handling.
agent = Agent(
...,
stt=cartesia.STT(),
tts=cartesia.TTS(),
)
Send text to convert to speech
The send_iter() method sends the text passed in for the service to synthesize
and yields TTSOutputChunks containing the produced PCM audio.
async for chunk in tts.send_iter("Demo text you want AI voice to say"):
pass
Metadata
Release files for vision-agents-plugins-cartesia 0.6.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vision_agents_plugins_cartesia-0.6.9.tar.gz | 7.0 kB | Without provenance | Details for vision_agents_plugins_cartesia-0.6.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vision_agents_plugins_cartesia-0.6.9-py3-none-any.whl | Python 3 | none | any | Details for vision_agents_plugins_cartesia-0.6.9-py3-none-any.whl |
Total release size: 14.6 kB
Release files / vision_agents_plugins_cartesia-0.6.9.tar.gz
| Download URL | vision_agents_plugins_cartesia-0.6.9.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
06d71f4eeacd19f04754b57ede95d13b52adeb9eb13facadca7097cbf619ebcc
|
|
BLAKE2b-256 checksum How to use checksums |
7b9cceefebaa676d1e1c5a9a0dcf2403d0bb64d4eb268b2e42ebc4d395e62885
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / vision_agents_plugins_cartesia-0.6.9-py3-none-any.whl
| Download URL | vision_agents_plugins_cartesia-0.6.9-py3-none-any.whl |
|---|---|
| Size | 7.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
74b2b80e24e5fd1165181073f6fffb6d848458fd666a5bac402fe16cef242d75
|
|
BLAKE2b-256 checksum How to use checksums |
52f86f7d3abdb9d6e62f32d52fe104fd221eb7d7cca1b56aa199dbd51f7f02ea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for vision-agents-plugins-cartesia 0.6.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.