product updateOpenAI

OpenAI Python SDK v2.27.0 adds Sora video API improvements and character support

TL;DR

OpenAI released version 2.27.0 of its Python SDK on March 13, 2026, adding significant improvements to the Sora video generation API. The update introduces character API support, video extension and editing capabilities, and higher resolution export options.

1 min read
0

OpenAI has released v2.27.0 of its Python SDK, the latest update to the official library for integrating OpenAI APIs into Python applications.

Key Changes

The release centers on expanding Sora video generation capabilities. The primary feature addition is Sora API improvements, which include:

  • Character API: Introduces character-based controls for video generation
  • Video extensions and edits: Enables developers to extend existing videos and apply targeted edits
  • Higher resolution exports: Supports video output at elevated resolutions

These features appear designed to give developers more granular control over video generation workflows, moving beyond simple prompt-to-video creation toward more iterative and controlled editing capabilities.

Technical Updates

Beyond the Sora enhancements, v2.27.0 includes:

  • API schema updates: General API definition updates reflected across the SDK
  • Bug fixes: Repair of the merged videos resource, addressing a previously broken endpoint
  • Infrastructure improvements: WebSocket protocol alignment and proper capitalization standardization
  • Codegen updates: Internal tooling changes for SDK code generation

The bug fix for the merged videos resource suggests this functionality had issues in v2.26.0 that are now resolved.

What This Means

The Sora API improvements indicate OpenAI is prioritizing video generation as a development platform, not just an internal capability. The addition of character controls and editing features suggests the company is moving toward production-ready video generation workflows that support professional use cases requiring iterative refinement rather than one-shot generation.

Developers using the Python SDK should update to access these new Sora capabilities. The merged videos resource fix is a necessary update for anyone relying on that functionality.

For context, the OpenAI Python SDK serves as the primary interface for developers building applications with OpenAI's APIs, making each release significant for the developer ecosystem. This version demonstrates continued investment in expanding Sora's feature set beyond basic video generation.

Related Articles

product update

OpenAI launches Trusted Contact feature allowing ChatGPT to alert designated friends during suicide risk

OpenAI has launched Trusted Contact for ChatGPT, allowing users 18+ to designate one adult contact who can be notified if the company's trained human review team detects serious self-harm risk. The feature comes after over 1 million of ChatGPT's 800 million weekly users expressed suicidal thoughts in conversations, and follows a 2025 wrongful death lawsuit.

product update

GitHub Reduces Token Usage in Copilot Agentic Workflows Running on Pull Requests

GitHub has optimized token usage in its production agentic workflows that run on every pull request. The company instrumented its own Copilot workflows to identify inefficiencies and built agents to address them, aiming to reduce accumulated API costs.

product update

OpenAI launches GPT-Realtime-2 with GPT-5-class reasoning, adds real-time translation across 70 languages

OpenAI has added three voice intelligence features to its Realtime API: GPT-Realtime-2 with GPT-5-class reasoning for complex conversational requests, GPT-Realtime-Translate supporting 70 input languages and 13 output languages, and GPT-Realtime-Whisper for live speech-to-text transcription. Translation and transcription are billed by the minute, while GPT-Realtime-2 uses token-based pricing.

model release

OpenAI releases GPT-5.5-Cyber for vetted security teams with relaxed safeguards

OpenAI released GPT-5.5-Cyber in limited preview on Thursday, a variant of its GPT-5.5 model with relaxed safeguards for vetted cybersecurity teams. The model is trained to be more permissive on security-related tasks including vulnerability identification, patch validation, and malware analysis.

Comments

Loading...