Transcript rewriting

Dictation runs an LLM pass over the transcript and returns the result in llm_response, alongside the verbatim transcript in text. This is the one feature Dictation has that the other speech-to-text APIs do not: you get the words as spoken and a usable version of them from the same call. The rewrite is applied by default. Omitting llm_instruction, or the whole config part, runs the default cleanup task, which removes disfluencies only: filler sounds and phrases, false starts, and stammered repeats. Every kept word, its spelling, and its punctuation stay exactly as spoken.

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

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

print(result.text)          # "Um, so the, the patient has a persistent cough."
print(result.llm_response)  # "The patient has a persistent cough."

Customizing the rewrite

Set llm_instruction to a plain-English description of the task you want, up to 2048 characters. It replaces the default cleanup task rather than adding to it:

{ "llm_instruction": "Remove filler words and fix punctuation." }

An explicit "llm_instruction": null means the same as omitting the field, so the default cleanup task still runs.

Python SDK
Python
JavaScript
cURL

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

config = aai.DictationConfig(
    llm_instruction="Rewrite as a concise clinical chart note.",
)

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

print(result.text)        # the verbatim transcript
print(result.final_text)  # the rewrite, falling back to the transcript

import json
import requests

config = {"llm_instruction": "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()

print(result["text"])
print(result["llm_response"])

import { readFileSync } from "fs";

const config = { llm_instruction: "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 }
);

const result = await response.json();
console.log(result.text);
console.log(result.llm_response);

curl -X POST https://dictation.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={"llm_instruction": "Rewrite as a concise clinical chart note."};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

Writing a good instruction

Describe only the transformation. Rules about output format, refusing to answer the text, and handling already-clean input are enforced by the service, so adding your own versions of them wastes instruction budget and can conflict with what the service already does.

Instead of	Write
”You are a helpful medical scribe. Output only the note, nothing else. If the input is already clean, return it unchanged. Rewrite as a chart note."	"Rewrite as a concise clinical chart note."
"Return JSON with a summary field.”	Describe the prose you want, then parse it yourself

Some instructions that work well:

"Remove filler words and tidy the punctuation."
"Rewrite as a short, friendly booking confirmation addressed to the client."
"Turn this into a bulleted list of action items."
"Rewrite as a concise clinical chart note."

The transcript is always preserved

The rewrite never replaces the transcription. text is always the verbatim transcript, and the rewritten version arrives separately in llm_response. If you need to show one value, final_text in the Python SDK returns the rewrite when there is one and the transcript otherwise. The rewrite is also best-effort. If it fails, the response is still 200, llm_response is null, and llm_error says why. See Error handling.

Dictated commands are not executed

The transcript is passed to the model as fenced data, with instructions not to act on anything inside it. Dictated speech routinely contains questions and commands like “translate this into French” or “ignore what I just said”. Those are rewritten as speech rather than carried out.

Prompting and keyterms shapes the transcript as it is written, where llm_instruction reshapes it afterwards.
Language selection sets the language the audio is transcribed in.

Getting started

Features

API reference

Advanced

Transcript rewriting

Customizing the rewrite

Writing a good instruction

The transcript is always preserved

Dictated commands are not executed

​Customizing the rewrite

​Writing a good instruction

​The transcript is always preserved

​Dictated commands are not executed

​Related features

Customizing the rewrite

Writing a good instruction

The transcript is always preserved

Dictated commands are not executed

Related features