---

AssemblyAI Ruby SDK

The AssemblyAI Ruby SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async, audio intelligence models, as well as the latest LeMUR models. We're working on adding real-time transcription to the Ruby SDK.

Documentation

Visit the AssemblyAI documentation for step-by-step instructions and a lot more details about our AI models and API.

Quickstart

Install the gem and add to the application's Gemfile by executing:

bundle add assemblyai

If bundler is not being used to manage dependencies, install the gem by executing:

gem install assemblyai

Import the AssemblyAI package and create an AssemblyAI object with your API key:

require 'assemblyai'

client = AssemblyAI::Client.new(api_key: 'YOUR_API_KEY')

You can now use the client object to interact with the AssemblyAI API.

Speech-To-Text

Transcribe an audio file with a public URL

transcript = client.transcripts.transcribe(
  audio_url: 'https://storage.googleapis.com/aai-web-samples/espn-bears.m4a',
)

transcribe queues a transcription job and polls it until the status is completed or error.

If you don't want to wait until the transcript is ready, you can use submit:

transcript = client.transcripts.submit(
  audio_url: 'https://storage.googleapis.com/aai-web-samples/espn-bears.m4a'
)

Transcribe a local audio file

uploaded_file = client.files.upload(file: '/path/to/your/file')
# You can also pass an IO object or base64 string
# uploaded_file = client.files.upload(file: File.new('/path/to/your/file')

transcript = client.transcripts.transcribe(audio_url: uploaded_file.upload_url)
puts transcript.text

transcribe queues a transcription job and polls it until the status is completed or error.

If you don't want to wait until the transcript is ready, you can use submit:

transcript = client.transcripts.submit(audio_url: uploaded_file.upload_url)

Enable additional AI models

You can extract even more insights from the audio by enabling any of our AI models using transcription options. For example, here's how to enable Speaker diarization model to detect who said what.

transcript = client.transcripts.transcribe(
  audio_url: audio_url,
  speaker_labels: true
)

transcript.utterances.each do |utterance|
  printf('Speaker %<speaker>s: %<text>s', speaker: utterance.speaker, text: utterance.text)
end

Get a transcript

This will return the transcript object in its current state. If the transcript is still processing, the status field will be queued or processing. Once the transcript is complete, the status field will be completed.

transcript = client.transcripts.get(transcript_id: transcript.id)

Get sentences and paragraphs

sentences = client.transcripts.get_sentences(transcript_id: transcript.id)
p sentences

paragraphs = client.transcripts.get_paragraphs(transcript_id: transcript.id)
p paragraphs

Get subtitles

srt = client.transcripts.get_subtitles(
  transcript_id: transcript.id,
  subtitle_format: AssemblyAI::Transcripts::SubtitleFormat::SRT
)
srt = client.transcripts.get_subtitles(
  transcript_id: transcript.id,
  subtitle_format: AssemblyAI::Transcripts::SubtitleFormat::SRT,
  chars_per_caption: 32
)

vtt = client.transcripts.get_subtitles(
  transcript_id: transcript.id,
  subtitle_format: AssemblyAI::Transcripts::SubtitleFormat::VTT
)
vtt = client.transcripts.get_subtitles(
  transcript_id: transcript.id,
  subtitle_format: AssemblyAI::Transcripts::SubtitleFormat::VTT,
  chars_per_caption: 32
)

List transcripts

This will return a page of transcripts you created.

page = client.transcripts.list

You can pass parameters to .list to filter the transcripts. To paginate over all pages, subsequently, use the .list_by_url method.

loop do
  page = client.transcripts.list_by_url(url: page.page_details.prev_url)
  break if page.page_details.prev_url.nil?
end

Delete a transcript

response = client.transcripts.delete(transcript_id: transcript.id)

Apply LLMs to your audio with LeMUR

Call LeMUR endpoints to apply LLMs to your transcript.

Prompt your audio with LeMUR

response = client.lemur.task(
  transcript_ids: ['0d295578-8c75-421a-885a-2c487f188927'],
  prompt: 'Write a haiku about this conversation.'
)

Summarize with LeMUR

response = client.lemur.summary(
  transcript_ids: ['0d295578-8c75-421a-885a-2c487f188927'],
  answer_format: 'one sentence',
  context: {
    'speakers': ['Alex', 'Bob']
  }
)

Ask questions

response = client.lemur.question_answer(
  transcript_ids: ['0d295578-8c75-421a-885a-2c487f188927'],
  questions: [
    {
      question: 'What are they discussing?',
      answer_format: 'text'
    }
  ]
)

Generate action items

response = client.lemur.action_items(
  transcript_ids: ['0d295578-8c75-421a-885a-2c487f188927']
)

Delete LeMUR request

response = client.lemur.task(...)
deletion_response = client.lemur.purge_request_data(request_id: response.request_id)