Kokoro TTS adds Kitten and Pocket TTS models along with WebGPU and CoreML runtime support

// 3h agoPRODUCT UPDATE

Kokoro TTS adds Kitten and Pocket TTS models along with WebGPU and CoreML runtime support

Developer @kmdrfx announced an update introducing support for Kitten and Pocket TTS models alongside WebGPU and CoreML execution runtimes for Kokoro TTS. The update adds runtime resource and performance monitoring features, while the author explores packaging the Kokoro runtime into an npm package for cross-platform WebGPU, CoreML, and Python deployment.

// ANALYSIS

Hardware-accelerated local TTS runtimes are bridging the gap between web applications and low-latency voice synthesis.

–WebGPU and CoreML runtimes enable private, hardware-accelerated text-to-speech directly on web browsers and Apple devices without server roundtrips.
–Integrating lightweight Kitten and Pocket TTS models provides developer flexibility for deployment in resource-constrained environments.
–Developing an npm package wrapper will make on-device TTS integration far more accessible to web developers.

// TAGS

kokorottswebgpucoremlspeechartificial-intelligence

DISCOVERED

3h ago

2026-07-27

PUBLISHED

1d ago

2026-07-26

RELEVANCE

7/ 10

AUTHOR

kmdrfx

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE25m ago

OpenCode 1.18.6 fixes MCP refresh and branch caches

OpenCode version 1.18.6 introduces key stability fixes and performance improvements across its desktop application and underlying client interfaces. This update resolves provider and Model Context Protocol (MCP) refresh issues in App v1, stabilizes v2 client compatibility by pinning the UI to a versioned `@opencode-ai/client` snapshot, and isolates remote reference caches by git branch to prevent cross-branch state collisions.

OPEN SOURCE1h ago

ESP32 AI Runs 28.9M Model at 9.5 Tokens/Sec

ESP32 AI is an architectural experiment by slvDev that runs a 28.9-million-parameter TinyStories language model locally on an $8 ESP32-S3 microchip without relying on external cloud servers. By keeping a 25-million-parameter embedding table in memory-mapped SPI flash to fetch token rows on demand, the project successfully circumvents tight microcontroller RAM limitations while maintaining a generation throughput of approximately 9.5 tokens per second.

OPEN SOURCE1h ago

Open Science v0.7.2 boosts research workflow transparency

AIPOCH has released Open Science v0.7.2, an update to its open-source, model-agnostic AI workbench for scientific discovery. The new release prioritizes making AI research workflows more transparent, controllable, and easier to manage as researchers increasingly rely on autonomous agents for complex scientific tasks.