Generate

Turn any video
into any text.

Explore your video through language. Generate any text, from summaries, highlights and hashtags to customized reports that look deeper and enable whole new uses.

Products

For Developers

Company

Illustrations
Illustrations

Generate 01

Generate across formats

Use prompts to generate accurate, useful text formats — from Q&As and titles to detailed content reports — and streamline your video-centric workflows.

Generate 01

Generate across formats

Use prompts to generate accurate, useful text formats — from Q&As and titles to detailed content reports — and streamline your video-centric workflows.

Illustrations

Generate 02

Summarize any content

Synthesize content to create concise and efficient descriptions, highlights, and chapters useful for content management, exploration, and understanding.

Generate 02

Summarize any content

Synthesize content to create concise and efficient descriptions, highlights, and chapters useful for content management, exploration, and understanding.

Illustrations

Generate 03

Ideate and create

Create topic categories and hashtags helpful for marketing and advertising, and get creative suggestions to help your team develop fresh new ideas.

Generate 03

Ideate and create

Create topic categories and hashtags helpful for marketing and advertising, and get creative suggestions to help your team develop fresh new ideas.

Actions worth a thousand words.

Drawing illustration
Any text format, from any video.

From Q&As and hashtag generation to detailed content reports.

Drawing illustration
Fast and accurate chapterization

Generate titles, headings, and chapters in seconds.

Drawing illustration
Text prompt generation

Index once, then generate boundless text prompts.

Drawing illustration
Content summarization

Get immediate, high-quality summaries of any video.

Drawing illustration
Metadata generation

Move beyond manual tagging to instant metadata creation.

Drawing illustration
Content analysis and incident reporting

Get time-stamped verbal descriptions of events captured on footage.

Actions worth a
thousand words.

Drawing illustration
Any text format, from any video.

From Q&As and hashtag generation to detailed content reports.

Drawing illustration
Fast and accurate chapterization

Generate titles, headings, and chapters in seconds.

Drawing illustration
Text prompt generation

Index once, then generate boundless text prompts.

Drawing illustration
Content summarization

Get immediate, high-quality summaries of any video.

Drawing illustration
Metadata generation

Move beyond manual tagging to instant metadata creation.

Drawing illustration
Content analysis and incident reporting

Get time-stamped verbal descriptions of events captured on footage.

Actions worth a thousand words.

Drawing illustration
Any text format, from any video.

From Q&As and hashtag generation to detailed content reports.

Drawing illustration
Fast and accurate chapterization

Generate titles, headings, and chapters in seconds.

Drawing illustration
Text prompt generation

Index once, then generate boundless text prompts.

Drawing illustration
Content summarization

Get immediate, high-quality summaries of any video.

Drawing illustration
Metadata generation

Move beyond manual tagging to instant metadata creation.

Drawing illustration
Content analysis and incident reporting

Get time-stamped verbal descriptions of events captured on footage.

Sample Apps

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs(<"YOUR_API_KEY">)

# Create new Index
index = client.index.create(
      name="My First Index",
      engines=[
          {
              "name": "pegasus1.2",
              "options": ["visual", "audio"],
          },
      ],
   )

# Create new Task on Index (Upload video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Generate Open-ended text from your video
prompt = "Give me an analysis of how the advertisement uses facial expressions to convey its message."
res = client.generate.text(task.video_id, prompt)
print(res.data)

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs(<"YOUR_API_KEY">)

# Create new Index
index = client.index.create(
      name="My First Index",
      engines=[
          {
              "name": "pegasus1.2",
              "options": ["visual", "audio"],
          },
      ],
   )

# Create new Task on Index (Upload video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Generate Open-ended text from your video
prompt = "Give me an analysis of how the advertisement uses facial expressions to convey its message."
res = client.generate.text(task.video_id, prompt)
print(res.data)

Python

Node

from twelvelabs import TwelveLabs
import os

client = TwelveLabs(<"YOUR_API_KEY">)

# Create new Index
index = client.index.create(
      name="My First Index",
      engines=[
          {
              "name": "pegasus1.2",
              "options": ["visual", "audio"],
          },
      ],
   )

# Create new Task on Index (Upload video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Generate Open-ended text from your video
prompt = "Give me an analysis of how the advertisement uses facial expressions to convey its message."
res = client.generate.text(task.video_id, prompt)
print(res.data)

Integrate with your personalized SDK — and your vision.

Deploy your custom-trained model on any cloud. See and surface everything in your video, then go beyond with AI that can realize your most game-changing ideas.

Thread cover

Your videos can speak volumes.

Try out TwelveLabs on your own videos and unlock their full potential.

threads-orange

Your videos can speak volumes.

Try out TwelveLabs on your own videos and unlock their full potential.