Sieve is a platform designed for developers to leverage advanced video and audio AI capabilities through a suite of APIs. It offers functionalities such as dubbing, speech transcription, and video editing, allowing users to customize applications for various use cases while managing costs and performance. The platform supports multiple languages and voice engines, enabling seamless integration of AI-driven features into existing workflows.
High-quality, performant APIs designed for video AI applications, including dubbing, visual QA, and auto-cropping.
Customizable platform for developers to build and deploy AI applications, allowing trade-offs between cost, quality, and speed.
Fast, scalable infrastructure that automatically adjusts to traffic demands without extra configuration.
Comprehensive observability stack providing logs and metrics for full visibility of operations.
Flexible pricing model based on actual usage, enabling cost control for developers.
Dubbing: Localize video or audio content into multiple languages while preserving the original tone and style, with options for various voice and translation engines.
Auto Crop: Automatically crop videos to specific aspect ratios based on subject detection and speaker tracking.
Active Speaker Detection: Identify and track active speakers in video content for enhanced audio-visual analysis.
Speech Transcription: Convert audio content into text with options for word-level timestamps and speaker diarization.
Lipsync: Synchronize dubbed audio with the original video to create a more natural viewing experience.
Provides high-quality, automated dubbing for video and audio content, enabling localization in multiple languages while preserving the original tone and style.
Offers a flexible platform for developers to customize applications according to specific cost, quality, and performance requirements.
Supports real-time processing, allowing for faster dubbing and transcription, which enhances productivity for content creators.
Includes advanced features like lip-syncing and background audio preservation, improving the naturalness and quality of dubbed content.
Facilitates integration with various voice and translation engines, giving users the ability to choose based on their specific needs and preferences.
Starter Plan: $0/month + usage, includes $20 free credit, public apps, custom function deployment, up to 3 concurrent requests, and standard support.
Production Plan: Custom pricing, includes $20 free credit, usage discounts, public apps, custom function deployment, custom concurrency, unlimited organization seats, 24x7 customer support, dedicated Slack channel, and custom integration support.
Dubbing (ElevenLabs voice): $0.535 per minute processed.
Dubbing (OpenAI voice): $0.402 per minute processed.
Speech Transcription: $0.15 per hour processed.
