ElevenAgents
ElevenLabs announced that the ElevenAgents API (/v1/convai) will enforce server-side request timeouts beginning November 26, 2026. Developers should implement client-side error handling for potential HTTP 504 responses during latency spikes.
Also shipped Nov 16, 2026ElevenLabs in November 2026 →
Deferred tier for asynchronous model calls on the Interactions API
Google Cloud announced general availability for the Deferred tier on the Gemini Enterprise Agent Platform. It offers a 50% discount compared to Standard PayGo rates for asynchronous Gemini model calls, providing a 24-hour completion window and 7-day state retention.
DeepSeek-V4.1-Flash-1017 is available in Public Preview
DeepSeek-V4.1-Flash-1017 is available in public preview as a fully managed model in Vertex AI Model Garden. The updated model features improved reasoning, coding, agentic, and visual capabilities, supporting multimodal inputs with up to 1M context tokens.
OpenAI CSAM Image Classifier is now available at no cost for approved organizations
OpenAI made its CSAM Image Classifier available at no cost to approved organizations. The tool returns separate classification signals for potential child sexual abuse material and potential AI-generated CSAM to assist human review processes.
Budget limit increased to 40,000 budgets per account
GitHub increased the maximum budget limit for GitHub Enterprise Cloud accounts from 10,000 to 40,000 budgets. The limit applies automatically on github.com and GHE.com to support organizations managing spending across many users and cost centers.
Workforce Identity Federation is GA for Looker Google Cloud core instances
Workforce Identity Federation is now generally available as the primary authentication method for Looker (Google Cloud core) instances using public secure, private, or hybrid connections. It can be configured using the Google Cloud console or gcloud CLI during instance creation or updates.
GitHub Copilot models deprecated on November 16, 2026
GitHub deprecated Claude Opus 4.8, Claude Opus 5, and GPT-5.6 Terra across most GitHub Copilot features. Alternative models including Claude Opus 5.5 and GPT-6 variants are automatically enabled for Copilot Enterprise and Business subscriptions under standard settings.
More from ElevenLabsEvery ElevenLabs release →
Tools as code
ElevenLabs now allows developers to build tools as code using the Python and JavaScript SDKs. The tool builder ensures consistency and allows tools to be managed entirely within the SDK.
Lower Speech to Text prices
ElevenLabs has reduced prices for Speech to Text services to $0.20 per hour for batch transcription and $0.22 per hour for real-time transcription on self-serve and Business plans.
Content Provenance API
ElevenLabs has released a beta endpoint to check audio files for an ElevenLabs watermark. The API returns detection status and generation metadata without exposing user prompts or account details.
Build and publish agents from the hosted MCP
ElevenLabs has added 39 tools to its hosted MCP, enabling users to build, edit, and publish ElevenAgents from any MCP client. Edits are staged in a draft before being published.
All changes: JavaScript SDK
The ElevenLabs JavaScript SDK has been updated to v2.79.0, adding a tool builder for defining webhook, client, and system tools, and introducing the reception client for the Reception API.
All changes: Python SDK
ElevenLabs Python SDK updates v2.78.0 and v2.79.0 add Gemini streaming answer text preservation, a tool builder module in elevenlabs.agent_tools, unhandled client tool call callbacks, and Reception API support.
All changes: ElevenLabs CLI
ElevenLabs CLI updates v1.9.2 through v1.12.1 add support for JSON, YAML, and TOML configuration formats, sparse config pulling, and terminal or Mermaid tool diagram rendering.
All changes: Packages
ElevenLabs updated its client and widget packages with post-set WebRTC volume controls, specific disconnect reason handling for LiveKit connection failures, typing indicators, and a full-page layout attribute.