Cloud endpoints & data residency

Choose the endpoint that best fits your application’s requirements, whether that’s routing to the nearest data center for the lowest latency or processing your data within a specific geographic region.* Note: File names may be processed by our subprocessors CrowdStrike and Datadog, which are located in the US. Do not include PII or PHI in file names if you require that information to remain in your selected data residency zone. *AssemblyAI will store Account Data and Usage Data in the United States, per our Privacy Policy and the Data Privacy Framework. Audio, transcript, and prompt data will be stored in the endpoint region you select. Incident response and customer support may be conducted from locations where staff are employed, which may be in the US, EU, or elsewhere. If your audio, transcript, or prompt needs to be accessed for debugging, a member of our team located outside of your endpoint region may access that data and may use a US-based subprocessor to support the troubleshooting or customer support request.

Data processing locations

All Dictation audio and transcription data is processed in AWS regions located in the United States and the European Union: US

AWS region	Location
`us-east-1`	N. Virginia
`us-east-2`	Ohio
`us-west-1`	N. California
`us-west-2`	Oregon

AWS region	Location
`eu-central-1`	Frankfurt
`eu-north-1`	Stockholm
`eu-south-1`	Milan
`eu-south-2`	Spain
`eu-west-1`	Ireland
`eu-west-3`	Paris

Which of these locations processes your data depends on the endpoint you call, as described below.

Endpoints

Endpoint	URL	Region
Global (default)	`https://dictation.assemblyai.com`	Nearest region
US data residency	`https://dictation.us.assemblyai.com`	US locations listed above
EU data residency	`https://dictation.eu.assemblyai.com`	EU locations listed above

The request format, headers, and parameters are identical on all three. Only the host changes. Each host serves both /v1/transcribe/live and /v1/transcribe.

The global endpoint routes to the nearest available region, so your data may be processed in any of the US or EU locations listed above. If you need data to stay in one of those zones, call the US or EU endpoint explicitly rather than relying on the default.

Which endpoint should I use?

Optimizing for latency? Use the Global endpoint (dictation.assemblyai.com). It routes your request to the region with the fastest response time for you, and needs no configuration change.
Need US data residency? Use the US endpoint (dictation.us.assemblyai.com).
Need EU data residency? Use the EU endpoint (dictation.eu.assemblyai.com).

How to use it

Replace the base URL with the endpoint you want. In the Python SDK the base URL comes from the dictation_base_url setting, which defaults to the global endpoint. The examples below use the US data zone; for the EU data zone, replace us with eu.

Python SDK
Python
JavaScript
cURL

Global (default)

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

result = aai.DictationTranscriber().transcribe_live("clip.wav")
print(result.text)

US data residency

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"
aai.settings.dictation_base_url = "https://dictation.us.assemblyai.com"

result = aai.DictationTranscriber().transcribe_live("clip.wav")
print(result.text)

EU data residency

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"
aai.settings.dictation_base_url = "https://dictation.eu.assemblyai.com"

result = aai.DictationTranscriber().transcribe_live("clip.wav")
print(result.text)

Global (default)

import requests

with open("clip.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://dictation.assemblyai.com/v1/transcribe/live",
    headers={"Authorization": "<YOUR_API_KEY>"},
    files={
        "config": (None, "{}", "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
print(response.json()["text"])

US data residency

import requests

with open("clip.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://dictation.us.assemblyai.com/v1/transcribe/live",
    headers={"Authorization": "<YOUR_API_KEY>"},
    files={
        "config": (None, "{}", "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
print(response.json()["text"])

EU data residency

import requests

with open("clip.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://dictation.eu.assemblyai.com/v1/transcribe/live",
    headers={"Authorization": "<YOUR_API_KEY>"},
    files={
        "config": (None, "{}", "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
print(response.json()["text"])

Global (default)

import { readFileSync } from "fs";

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append("config", new Blob(["{}"], { type: "application/json" }));
form.append("audio", new Blob([audio], { type: "audio/wav" }), "clip.wav");

const response = await fetch(
  "https://dictation.assemblyai.com/v1/transcribe/live",
  { method: "POST", headers: { Authorization: "<YOUR_API_KEY>" }, body: form }
);
console.log((await response.json()).text);

US data residency

import { readFileSync } from "fs";

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append("config", new Blob(["{}"], { type: "application/json" }));
form.append("audio", new Blob([audio], { type: "audio/wav" }), "clip.wav");

const response = await fetch(
  "https://dictation.us.assemblyai.com/v1/transcribe/live",
  { method: "POST", headers: { Authorization: "<YOUR_API_KEY>" }, body: form }
);
console.log((await response.json()).text);

EU data residency

import { readFileSync } from "fs";

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append("config", new Blob(["{}"], { type: "application/json" }));
form.append("audio", new Blob([audio], { type: "audio/wav" }), "clip.wav");

const response = await fetch(
  "https://dictation.eu.assemblyai.com/v1/transcribe/live",
  { method: "POST", headers: { Authorization: "<YOUR_API_KEY>" }, body: form }
);
console.log((await response.json()).text);

Global (default)

curl -X POST https://dictation.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

US data residency

curl -X POST https://dictation.us.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

EU data residency

curl -X POST https://dictation.eu.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

Pre-warming is per host. A connection warmed against the global endpoint is no use to a request aimed at a data zone endpoint, so warm the same host you are about to transcribe against. See Connection pre-warming.

Getting started

Features

API reference

Advanced

Cloud endpoints & data residency

Data processing locations

Endpoints

Which endpoint should I use?

How to use it

​Data processing locations

​Endpoints

​Which endpoint should I use?

​How to use it

Data processing locations

Endpoints

Which endpoint should I use?

How to use it