Vercel Sandbox Drives enable persistent cross-instance storage
Mount reusable persistent storage directories across sandbox instances to preserve agent state and shared datasets without per-sandbox duplication.
Eliminates re-initialization overhead for multi-run agent workflows and enables read-only snapshots for parallel sandbox execution. Critical for stateful AI workloads that need workspace persistence and concurrent access patterns.
Replaces ad-hoc file handling and ephemeral sandbox storage for agent memory. Requires explicit Drive.create/getOrCreate calls and region affinity awareness. Worth trying now if running multi-turn or parallel agent tasks; pricing ($0.05/GB-month storage in iad1) is reasonable for typical workloads but monitor read/write costs ($0.0015/$0.004 per GB).
- “A Drive is persistent storage that you mount as a directory in a Vercel Sandbox. It isn't tied to a single sandbox, so you can reuse the same Drive across runs and different sandbox instances.”
- “A Drive supports one read-write mount at a time. After the Drive has been written to, multiple sandboxes can read from it concurrently by mounting point-in-time, read-only snapshots.”
- “storage costs $0.05 per GB-month, reads $0.0015 per GB, and writes $0.004 per GB”
- “Hobby includes 15 GB of Drive storage and 30 GB each of reads and writes per month”
vercel-sandboxpersistent-storageagent-workflowstypescript
Gemini 3.8 Flash TTS ships custom voice generation
Voice replication from 30-second samples, line-by-line performance direction, and 2,000+ production voices available now in Gemini API with SynthID watermarking and consent verification built in.
Replaces static voice presets with generative voice design across 100+ languages. Developers can scale from fixed voice libraries to infinite custom profiles, reducing audio asset production friction for games, audiobooks, and voice agents.
Ready to deploy. Start in Google AI Studio today to prototype custom voices and multi-speaker scenes. Requires familiarity with natural language prompts for voice direction and consent recording capture for replication. Worth trying now if you're building voice-heavy products; watermarking and consent tooling are already baked in.
- “Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS are our most expressive audio generation models yet”
- “Create entirely new voices from scratch using natural language prompts”
- “Access 2,000+ production-ready voices with broad language coverage”
- “Recreate consistent vocal profiles from just a 30-second audio sample”
- “Securing the #1 overall spot on Hume AI's Voice Design Benchmark (71.4)”
- “every audio clip generated by our Gemini Audio models is watermarked with SynthID”
text-to-speechvoice-synthesisgemini-apiaudio-generationmultilingual
Node.js 24.20.0 LTS ships async scope, stream iteration
AsyncLocalStorage gains using scopes for cleaner context binding, stream/iter moves to stable API, and JSPI WebAssembly support lands in production.
Using scopes eliminate manual context tracking boilerplate in async code; stream iteration standardization reduces fragmentation across async iteration patterns. For AI workloads, better async context isolation improves observability in concurrent operations.
Using scopes replace manual AsyncLocalStorage.run() wrapping—try it immediately if you manage deep async call stacks. Stream iteration replaces custom async iterator polyfills. Requires Node 24.20+; production-ready for LTS workloads, but audit permission audit mode needs explicit opt-in testing.
- “add using scopes to AsyncLocalStorage”
- “add node:stream/iter implementation”
- “enable JSPI”
- “update root certificates to NSS 3.125”
- “add permission.drop”
node-ltsasync-contextstreamswebassemblypermissions
Muse Image launches on AI Gateway with unified API
Meta's Muse Image handles both generation and editing in a single model call via AI SDK, replacing separate model switches.
Eliminates context switching between generation and editing models. Unified API reduces integration friction and simplifies image manipulation workflows for developers using Vercel's AI Gateway.
Replaces dual-model workflows. Requires: Vercel AI Gateway access, AI SDK integration, `meta/muse-image-1.0` model endpoint. Ready now—use `generateImage()` with `prompt.images` for reference blending or instruction-based editing. Worth trying if already on AI Gateway stack.
- “It is their first image model and a separate family from Muse Spark, returning images rather than text.”
- “One model does both, so you don't switch models to move from generating to editing.”
- “AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference”
image-generationapi-gatewaymeta-musevercelsdk
Google ships Gemini 3.8 Flash TTS with voice control
Line-by-line delivery direction and 2,000+ production voices via natural language prompts; Flash-Lite trades expressiveness for cost at scale.
Developers can now skip voice talent hiring for character generation and localization, with fine-grained pacing/dialect control per line. High-volume use cases (dubbing, agents) get cost-efficient alternatives without sacrificing tone control.
Replaces custom voice synthesis workflows and basic TTS pipelines. Requires Gemini API key; rolls out today via Gemini API and AI Studio. Worth trying now for dubbing/localization teams; production readiness depends on your language/dialect needs and consent verification complexity in your jurisdiction.
- “over 100 languages and dialects”
- “library scales from 30 original voices to more than 2,000 production-ready voices, including regional varieties like Mexican Spanish, Quebec French, and Scots English”
- “Flash TTS took the top spot on Hume AI's Voice Design Benchmark (71.4)”
- “developers can generate entirely new character voices from natural language prompts, direct delivery line by line (pacing, dialect, acting cues)”
- “Voice replication is not available in Illinois, Texas, the EEA, UK, Switzerland, or India”
text-to-speechvoice-synthesisgemini-apilocalizationcost-optimization