Export paragraphs and sentences | AssemblyAI

Supported languages

Global Englishen

Australian Englishen_au

British Englishen_uk

US Englishen_us

Spanishes

Frenchfr

Germande

Italianit

Portuguesept

Dutchnl

Hindihi

Finnishfi

Polishpl

Russianru

Ukrainianuk

Vietnamesevi

Albaniansq

Amharicam

Assameseas

Bashkirba

Basqueeu

Belarusianbe

Bosnianbs

Bretonbr

Bulgarianbg

Catalanca

Croatianhr

Czechcs

Danishda

Estonianet

Faroesefo

Galiciangl

Greekel

Gujaratigu

Haitianht

Hausaha

Hawaiianhaw

Hebrewhe

Hungarianhu

Icelandicis

Indonesianid

Javanesejw

Kazakhkk

Laolo

Latinla

Latvianlv

Lingalaln

Lithuanianlt

Luxembourgishlb

Macedonianmk

Malagasymg

Malayms

Maltesemt

Maorimi

Norwegianno

Norwegian Nynorsknn

Occitanoc

Pashtops

Romanianro

Sanskritsa

Serbiansr

Shonasn

Sindhisd

Slovaksk

Sloveniansl

Somaliso

Sundanesesu

Swahilisw

Swedishsv

Tagalogtl

Tajiktg

Tatartt

Tibetanbo

Turkmentk

Uzbekuz

Welshcy

Yiddishyi

Yorubayo

You can retrieve transcripts that are automatically segmented into paragraphs. The text of the transcript is broken down by paragraphs, along with additional metadata.

Export paragraphs

1 import assemblyai as aai
2 
3 aai.settings.api_key = "<YOUR_API_KEY>"
4 
5 # audio_file = "./local_file.mp3"
6 audio_file = "https://assembly.ai/wildfires.mp3"
7 
8 config = aai.TranscriptionConfig()
9 
10 transcript = aai.Transcriber(config=config).transcribe(audio_file)
11 
12 if transcript.status == "error":
13   raise RuntimeError(f"Transcription failed: {transcript.error}")
14 
15 paragraphs = transcript.get_paragraphs()
16 for paragraph in paragraphs:
17   print(paragraph.text)
18   print()

Export sentences

1 import assemblyai as aai
2 
3 aai.settings.api_key = "<YOUR_API_KEY>"
4 
5 # audio_file = "./local_file.mp3"
6 audio_file = "https://assembly.ai/wildfires.mp3"
7 
8 config = aai.TranscriptionConfig()
9 
10 transcript = aai.Transcriber(config=config).transcribe(audio_file)
11 
12 if transcript.status == "error":
13   raise RuntimeError(f"Transcription failed: {transcript.error}")
14 
15 sentences = transcript.get_sentences()
16 for sentence in sentences:
17   print(sentence.text)
18   print()

You can retrieve transcripts that are automatically segmented into sentences, for a more reader-friendly experience. The text of the transcript is broken down by sentences, along with additional metadata.

The response is an array of objects, each representing a sentence or a paragraph in the transcript. See the API reference for more info.