What changed in the tools we cover over the last 30 days. Older news drops off this page, and the recipes are kept current instead.
Put a pause marker in your text and Flux TTS waits. Spell a word in IPA and it says it your way (Early Access).
The official Node SDK now accepts grok_imagine_1_5_lite for text-to-video and image-to-video. Upgrade the package and swap the model.
Subtitles (.vtt), Markdown, iOS .strings, YAML, .properties, .resx, .xlsm, .odt, .rtf and SCORM .zip can now be uploaded for translation.
New eleven_v4 model: more expressive speech and better voice cloning in 90+ languages. eleven_v4_turbo answers in about 100 ms.
Since 2026-09-22 gemini-3.8-flash-tts and flash-lite-tts are GA, with 150+ voices, voice design and replication.
OpenAI shipped GPT-6 Sol and the low-cost GPT-6 Luna on 2026-09-22 for the Responses and Chat Completions APIs.
Google made gemini-3.8-flash GA on 2026-09-02: its most capable Flash model, with 1M-token input and function calling.
Sep 22, 2026: Claude Opus 5.5 ships with 1M context and adaptive thinking. Swap the model ID and check breaking changes.
langchain v1.4.0 (Sep 1, 2026) adds langchain.mcp: load any MCP server's tools into create_agent.
Since Sep 2, 2026, Pinecone indexes can mix BM25 keyword, dense and sparse fields in one schema. Exact-match SKUs and error codes.
New nova-3-pharma model tuned for pharmaceutical vocabulary and drug names; English, batch and streaming. Swap one model param.
Wirestack