www.sievedata.com Open in urlscan Pro
76.76.21.241  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Home

Explore

Blog

About

Pricing

Docs


Log inSign up
Join our Discord community!
Build better AI 

with multiple models

AI models are a new kind of building block. Sieve is the easiest way to use
these building blocks to understand audio, generate video, and much more — at
scale.
Get Started for FreeBook a Demo
Discover
State-of-the art models in just a few lines of code, and a curated set of
production-ready apps for many use cases.

autocrop

public
Smart, automatic cropping of a video to a given aspect ratio based on subject
detection and speaker tracking.
Featured
functionbuilt 14h ago


video_transcript_analyzer

public
Given a video or audio, generate a title, chapters, summary and tags
Featured
functionbuilt 1d ago


dubbing

public
Translate any video or audio to several languages
Featured
functionbuilt 8d ago


video_retalking

public
Sync lips in a video to any audio
Featured
functionbuilt 2d ago


speech_transcriber

public
Fast, high quality speech transcription with word-level timestamps and
translation capabilities
Featured
functionbuilt 6d ago


audio_enhancement

public
Remove background noise from audio and upsample it.
Featured
functionbuilt 2 months ago
Explore more apps
Design

Build complex AI apps
Import your favorite models like Python packages.
# Video dubbing in a few lines of code transcriber =
sieve.function.get("sieve/whisper") translator =
sieve.function.get("sieve/seamless_text2text") tts =
sieve.function.get("sieve/xtts") lipsyncer =
sieve.function.get("sieve/video_retalking") transcript =
transcriber.run(source_video) translated_text = translator.run(text, "eng",
language) speech = tts.run(source_audio, language, translated_text) dubbed_video
= lipsyncer.run(source_video, speech)

# Video dubbing in a few lines of code
transcriber = sieve.function.get("sieve/whisper")
translator = sieve.function.get("sieve/seamless_text2text")
tts = sieve.function.get("sieve/xtts")
lipsyncer = sieve.function.get("sieve/video_retalking")

transcript = transcriber.run(source_video)
translated_text = translator.run(text, "eng", language)
speech = tts.run(source_audio, language, translated_text)

dubbed_video = lipsyncer.run(source_video, speech)



Visualize and debug
Visualize results with auto-generated interfaces built for your entire team.

Run
Deploy custom code with ease
Define your environment and compute in code, and deploy with a single command.
import sieve @sieve.function( name="my_model", gpu=sieve.gpu.T4(),
python_packages=["torch==1.8.1"] ) def my_model(video: sieve.File): # do stuff

import sieve

@sieve.function(
  name="my_model",
  gpu=sieve.gpu.T4(),
  python_packages=["torch==1.8.1"]
)
def my_model(video: sieve.File):
  # do stuff



sieve deploy

sieve deploy


Infrastructure that just works
Fast, scalable infrastructure without the hassle.

Run at any scale

We built Sieve to automatically scale as your traffic increases with zero extra
configuration.

Stop worrying about Docker, CUDA, and GPUs

Package models with a simple Python decorator and deploy instantly.

Logs and metrics

A full-featured observability stack so you have full visibility of what’s
happening under the hood.

Flexible, compute-based pricing

Pay only for what you use, by the second. Gain full control over your costs.
Built for your use case

Work with the experts
We're a team of machine learning experts from places like Berkeley, NVIDIA,
Apple, Snapchat, Microsoft, and Scale AI. Work with us to support your custom
use case and integrate Sieve into your existing pipeline.

Schedule a demoJoin our Discord community

© Copyright 2024. All rights reserved.