Power your apps with world-class speech and Language AI models
- Documentation
- Installation
- Reference
- Usage
- Authentication
- Async Client
- Exception Handling
- Advanced Features
- Websockets
- Advanced
- Contributing
- Community Code of Conduct
- License
API reference documentation is available here.
pip install deepgram-sdkA full reference for this library is available here.
Instantiate and use the client with the following:
from deepgram import DeepgramClient
client = DeepgramClient(
api_key="YOUR_API_KEY",
)
client.listen.v1.media.transcribe_file()The Deepgram SDK supports two authentication methods:
Use access tokens for temporary or scoped access (recommended for client-side applications):
from deepgram import DeepgramClient
# Explicit access token
client = DeepgramClient(access_token="YOUR_ACCESS_TOKEN")
# Or via environment variable DEEPGRAM_TOKEN
client = DeepgramClient()
# Generate access tokens using your API key
auth_client = DeepgramClient(api_key="YOUR_API_KEY")
token_response = auth_client.auth.v1.tokens.grant()
token_client = DeepgramClient(access_token=token_response.access_token)Use your Deepgram API key for server-side applications:
from deepgram import DeepgramClient
# Explicit API key
client = DeepgramClient(api_key="YOUR_API_KEY")
# Or via environment variable DEEPGRAM_API_KEY
client = DeepgramClient()The SDK automatically discovers credentials from these environment variables:
DEEPGRAM_TOKEN- Your access token (takes precedence)DEEPGRAM_API_KEY- Your Deepgram API key
Precedence: Explicit parameters > Environment variables
The SDK also exports an async client so that you can make non-blocking calls to our API. Note that if you are constructing an Async httpx client class to pass into this client, use httpx.AsyncClient() instead of httpx.Client() (e.g. for the httpx_client parameter of this client).
import asyncio
from deepgram import AsyncDeepgramClient
client = AsyncDeepgramClient(
api_key="YOUR_API_KEY",
)
async def main() -> None:
await client.listen.v1.media.transcribe_file()
asyncio.run(main())When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error will be thrown.
from deepgram.core.api_error import ApiError
try:
client.listen.v1.media.transcribe_file(...)
except ApiError as e:
print(e.status_code)
print(e.body)Access raw HTTP response data including headers:
from deepgram import DeepgramClient
client = DeepgramClient()
response = client.listen.v1.media.with_raw_response.transcribe_file(
request=audio_data,
model="nova-3"
)
print(response.headers) # Access response headers
print(response.data) # Access the response objectConfigure timeouts, retries, and other request options:
from deepgram import DeepgramClient
# Global client configuration
client = DeepgramClient(timeout=30.0)
# Per-request configuration
response = client.listen.v1.media.transcribe_file(
request=audio_data,
model="nova-3",
request_options={
"timeout_in_seconds": 60,
"max_retries": 3
}
)Use a custom httpx client for advanced networking features:
import httpx
from deepgram import DeepgramClient
client = DeepgramClient(
httpx_client=httpx.Client(
proxies="http://proxy.example.com",
timeout=httpx.Timeout(30.0)
)
)The SDK automatically retries failed requests with exponential backoff:
# Automatic retries for 408, 429, and 5xx status codes
response = client.listen.v1.media.transcribe_file(
request=audio_data,
model="nova-3",
request_options={"max_retries": 3}
)The SDK supports both sync and async websocket connections for real-time, low-latency communication. Sockets can be created using the connect method, which returns a context manager.
You can either iterate through the returned SocketClient to process messages as they arrive, or attach handlers to respond to specific events.
# Connect to the websocket (Sync)
import threading
from deepgram import DeepgramClient
client = DeepgramClient(...)
with client.v1.connect() as socket:
# Iterate over the messages as they arrive
for message in socket
print(message)
# Or, attach handlers to specific events
socket.on(EventType.OPEN, lambda _: print("open"))
socket.on(EventType.MESSAGE, lambda message: print("received message", message))
socket.on(EventType.CLOSE, lambda _: print("close"))
socket.on(EventType.ERROR, lambda error: print("error", error))
# Start the listening loop in a background thread
listener_thread = threading.Thread(target=socket.start_listening, daemon=True)
listener_thread.start()# Connect to the websocket (Async)
import asyncio
from deepgram import AsyncDeepgramClient
client = AsyncDeepgramClient(...)
async with client.v1.connect() as socket:
# Iterate over the messages as they arrive
async for message in socket
print(message)
# Or, attach handlers to specific events
socket.on(EventType.OPEN, lambda _: print("open"))
socket.on(EventType.MESSAGE, lambda message: print("received message", message))
socket.on(EventType.CLOSE, lambda _: print("close"))
socket.on(EventType.ERROR, lambda error: print("error", error))
# Start listening for events in an asyncio task
listen_task = asyncio.create_task(socket.start_listening())The SDK provides access to raw response data, including headers, through the .with_raw_response property.
The .with_raw_response property returns a "raw" client that can be used to access the .headers and .data attributes.
from deepgram import DeepgramClient
client = DeepgramClient(
...,
)
response = client.listen.v1.media.with_raw_response.transcribe_file(...)
print(response.headers) # access the response headers
print(response.data) # access the underlying objectThe SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long as the request is deemed retryable and the number of retry attempts has not grown larger than the configured retry limit (default: 2).
A request is deemed retryable when any of the following HTTP status codes is returned:
Use the max_retries request option to configure this behavior.
client.listen.v1.media.transcribe_file(..., request_options={
"max_retries": 1
})The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.
from deepgram import DeepgramClient
client = DeepgramClient(
...,
timeout=20.0,
)
# Override timeout for a specific method
client.listen.v1.media.transcribe_file(..., request_options={
"timeout_in_seconds": 1
})You can override the httpx client to customize it for your use-case. Some common use-cases include support for proxies
and transports.
import httpx
from deepgram import DeepgramClient
client = DeepgramClient(
...,
httpx_client=httpx.Client(
proxy="http://my.test.proxy.example.com",
transport=httpx.HTTPTransport(local_address="0.0.0.0"),
),
)While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!
On the other hand, contributions to the README are always very welcome!
Please see our community code of conduct before contributing to this project.
This project is licensed under the MIT License - see the LICENSE file for details.