Examples - AssemblyAI

The knobs do different jobs. stt_prompt and keyterms_prompt steer the ASR model while it writes the transcript down — the first describes the situation, the second lists the exact terms to expect. llm_instruction tells the LLM what to do with that transcript after it is written.

Clinical dictation

A doctor dictating a visit note. stt_prompt tells the model what kind of audio this is, keyterms_prompt pins the exact drug names, and llm_instruction turns the spoken rambling into a chart-ready note.

Python SDK
Python
JavaScript
cURL

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

config = aai.DictationConfig(
    stt_prompt="A doctor dictating a patient visit note.",
    keyterms_prompt=["amoxicillin", "lisinopril", "metoprolol"],
    llm_instruction=(
        "Remove filler words and rewrite as a concise clinical chart note."
    ),
)

result = aai.DictationTranscriber().transcribe_live("clip.wav", config)

transcript = result.text
rewrite = result.final_text  # the cleaned-up text, falling back to the transcript

import json
import requests

config = {
    "stt_prompt": "A doctor dictating a patient visit note.",
    "keyterms_prompt": ["amoxicillin", "lisinopril", "metoprolol"],
    "llm_instruction": (
        "Remove filler words and rewrite as a concise clinical chart note."
    ),
}

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, json.dumps(config), "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
result = response.json()

transcript = result["text"]
rewrite = result["llm_response"] or transcript  # fall back on rewrite failure

import { readFileSync } from "fs";

const config = {
  stt_prompt: "A doctor dictating a patient visit note.",
  keyterms_prompt: ["amoxicillin", "lisinopril", "metoprolol"],
  llm_instruction:
    "Remove filler words and rewrite as a concise clinical chart note.",
};

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append(
  "config",
  new Blob([JSON.stringify(config)], { 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,
});

if (!response.ok) {
  const error = await response.json();
  throw new Error(error.error || error.detail);
}

const result = await response.json();
const transcript = result.text;
const rewrite = result.llm_response ?? transcript; // fall back on rewrite failure

curl -X POST https://dictation.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={"stt_prompt": "A doctor dictating a patient visit note.", "keyterms_prompt": ["amoxicillin", "lisinopril", "metoprolol"], "llm_instruction": "Remove filler words and rewrite as a concise clinical chart note."};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

Travel booking summary

A travel agent dictating a client booking summary. keyterms_prompt pins the specific destination and airline names, and llm_instruction reshapes the transcript into a confirmation the client can read.

Python SDK
Python
JavaScript
cURL

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

config = aai.DictationConfig(
    keyterms_prompt=["Reykjavik", "Cancun", "Lufthansa"],
    llm_instruction=(
        "Remove filler words and rewrite as a short, friendly booking "
        "confirmation addressed to the client."
    ),
)

result = aai.DictationTranscriber().transcribe_live("clip.wav", config)

transcript = result.text
rewrite = result.final_text  # the cleaned-up text, falling back to the transcript

import json
import requests

config = {
    "keyterms_prompt": ["Reykjavik", "Cancun", "Lufthansa"],
    "llm_instruction": (
        "Remove filler words and rewrite as a short, friendly booking "
        "confirmation addressed to the client."
    ),
}

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, json.dumps(config), "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
result = response.json()

transcript = result["text"]
rewrite = result["llm_response"] or transcript

import { readFileSync } from "fs";

const config = {
  keyterms_prompt: ["Reykjavik", "Cancun", "Lufthansa"],
  llm_instruction:
    "Remove filler words and rewrite as a short, friendly booking confirmation addressed to the client.",
};

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append(
  "config",
  new Blob([JSON.stringify(config)], { 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,
});

if (!response.ok) {
  const error = await response.json();
  throw new Error(error.error || error.detail);
}

const result = await response.json();
const transcript = result.text;
const rewrite = result.llm_response ?? transcript;

curl -X POST https://dictation.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={"keyterms_prompt": ["Reykjavik", "Cancun", "Lufthansa"], "llm_instruction": "Remove filler words and rewrite as a short, friendly booking confirmation addressed to the client."};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

Prompting and keyterms — what stt_prompt and keyterms_prompt each steer
Transcript rewriting — writing a good llm_instruction
Quickstart — the config reference these examples draw on