Summarization

Summarization generates concise summaries of transcribed content using AI intelligence. You can summarize audio during transcription or apply it to existing text transcripts. Summary length can be controlled using an optional parameter.

How to Enable

"enable_summarization": "true"

During Transcription

Parameters

  • enable_summarization (required): Set to "true"
  • summary_max_length (optional): Maximum summary length in characters

Request

Don’t forget to replace YOUR_API_KEY with your own secret key.
import requests

url = "https://tb2.shunyalabs.ai/v1/transcriptions"
headers = {"X-API-Key": "your-api-key"}

with open("team_meeting.wav", "rb") as f:
    files = {"file": f}
    data = {
        "enable_summarization": "true",
        "summary_max_length": "200"  # optional
    }

response = requests.post(
    url,
    headers=headers,
    files=files,
    data=data
)

print(response.json())

Standalone Summarization

Parameters

  • text (required): Input text to summarize (up to 10,000 characters)
  • summary_max_length (optional): Maximum summary length in characters

Request

Don’t forget to replace YOUR_API_KEY with your own secret key.
import requests

url = "https://tb.shunyalabs.ai/v1/summarize"
headers = {"X-API-Key": "your-api-key"}

data = {
    "text": "Long transcription text goes here...",
    "summary_max_length": "200"  # optional
}

response = requests.post(url, headers=headers, data=data)
print(response.json())

Example Output

{
  "summary": "The quarterly review showed 15% revenue growth, with strong performance in the enterprise segment. Key challenges include increased competition and rising customer acquisition costs. Strategic priorities for next quarter are product innovation and market expansion."
}

Best Practices

  • Choose summary length based on your use case
  • Longer inputs may require higher summary_max_length
  • Summaries perform best on coherent, complete conversations

Use Cases

  1. Meeting minutes and executive summaries
  2. TL;DR generation for podcasts and lectures
  3. Customer call summaries for CRM systems
  4. Research and interview insight extraction
  5. Audio/video content catalog descriptions
  6. Email-friendly summaries from meetings