sayzard1h ago

Show HN: NPM Package that fills forms via voice using Gemini Live API

audio-forms는 Gemini Live API를 활용해 React 애플리케이션에서 음성으로 폼을 자동 작성할 수 있는 오픈소스 컴포넌트입니다. 사용자는 마이크 버튼을 눌러 자연어로 입력하면, 서버가 음성 데이터를 받아 Gemini API로 전달해 필드를 실시간으로 채워줍니다. API 키는 서버에만 저장되어 보안성이 높고, 이름·이메일 등 민감한 필드는 모델이 철자 확인 후 입력하는 더블체크 모드도 지원합니다. React 앱에 쉽게 통합 가능하며, 복잡한 입력에 대응하는 사고 수준 조절 기능도 제공합니다.

https://www.npmjs.com/package/audio-forms

#react #voiceinput #geminiapi #formfilling #speechtotext

audio-forms

Fill forms with voice using Gemini Live API. Latest version: 0.1.0, last published: 6 minutes ago. Start using audio-forms in your project by running `npm i audio-forms`. There are no other projects in the npm registry using audio-forms.

npm
sayzard21h ago

⚙️ New Ollama Release! ⚙️
Version: v0.23.2
Release Notes:
## What's Changed

* `ollama launch` no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models.
* Use `ollama launch claude-desktop --restore` to restore Claude Desktop to its normal state.
* `/api/show` responses are now cached, improving median latency by **~6.7x** which will increase load speed for integrations like VS Code.
* Improved backup wor...

#Ollama #AI #LLM #Gemini #GeminiAPI

sayzard3d ago

⚙️ New Ollama Release! ⚙️
Version: v0.23.1
Release Notes:
## Gemma 4 MTP (Multi-token Processing) for the MLX runner
Gemma 4 MTP speculative decoding is now supported on Macs. This can give over a 2x speed increase for the Gemma 4 31B model on coding tasks.

```
ollama run gemma4:31b-coding-mtp-bf16
```

## What's Changed
* Update MLX and MLX-C with threading fixes by @dhiltgen in https://github.com/ollama/ollama/pull/15845
* go: bump to 1.26 by @...

#Ollama #AI #LLM #Gemini #GeminiAPI

Update MLX and MLX-C with threading fixes by dhiltgen · Pull Request #15845 · ollama/ollama

MLX now relies on OS-thread-local execution state for streams, encoders, and caches. Add an mlxthread executor backed by runtime.LockOSThread and route runner initialization, model load, inference,...

GitHub
sayzard5d ago

⚙️ New Ollama Release! ⚙️
Version: v0.23.0
Release Notes:
## Claude Desktop
Claude Desktop is now supported with Ollama Launch.

Claude Cowork and Claude Code are supported within the Claude Desktop App.

```
ollama launch claude-desktop
```

### Claude Cowork
<img width="1272" height="872" alt="ca1" src="https://github.com/user-attachments/assets/1d550e3f-0272-4429-8cb2-06d32344cb77" />

### Claude Code
<img width="1272" height="872" alt="...

#Ollama #AI #LLM #Gemini #GeminiAPI

AI SparkupApr 24

Gemini Deep Research API, MCP 연결로 기업 전용 데이터까지 자율 리서치

구글이 Gemini 3.1 Pro 기반 자율 리서치 에이전트 Deep Research와 Max를 API로 공개. MCP 지원으로 기업 전용 데이터까지 자율 탐색합니다.

https://aisparkup.com/posts/11735

Show threadmichabbbApr 23

→ Mindlid: 20% lift in top-1 recall for wellness app

🔗 Available via #GeminiAPI & #VertexAI
Integrates with #LangChain, #LlamaIndex, #Haystack, #Weaviate, #Qdrant, #ChromaDB & Vector Search
🧪 Colab notebooks for Gemini API & Vertex AI ready to use

🌐
https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-embedding-2-generally-available/

Gemini Embedding 2 is now generally available.

We’re announcing the general availability of Gemini Embedding 2 via the Gemini API and Vertex AI.

Google
WinbuzzerApr 16

https://winbuzzer.com/2026/04/16/google-launches-gemini-31-flash-tts-for-developers-xcxwbn/

Google Launches Gemini 3.1 Flash TTS in Preview

#AI #Gemini31FlashTTS #GeminiAPI #Google #GoogleGemini #GoogleAI #GoogleAIStudio #GenerativeAI #AIModels #AIAudio #AIVoiceGeneration #SpeechSynthesis #VoiceCloning

AIntelligenceHubApr 16
Google introduced prepay billing for Gemini API in AI Studio. Developers can top up credits, set auto-reload, and manage spend with clearer limits before month-end. This could help teams move prototypes to production with fewer budget shocks. https://aintelligencehub.com/articles/google-gemini-api-prepay-billing-2026?utm_source=mastodon&utm_medium=social&utm_campaign=organic_social&utm_content=google-gemini-api-prepay-billing-2026 #AI #GeminiAPI #Cloud #DeveloperTools
Google Adds Prepay Billing for Gemini API to Cut Surprise Spend

Google AI Studio now supports prepay credits for Gemini API usage, starting in the US for new billing accounts and rolling out globally in the coming weeks.

sayzardApr 3

Google AI Developers (@googleaidevs)

Gemini API에 비용과 안정성을 조절할 수 있는 새 추론 티어인 Flex와 Priority가 추가되었습니다. Flex는 비용 민감하고 지연 허용도가 높은 워크로드에 적합하며, Priority는 프리미엄 가격으로 가장 높은 신뢰성을 제공해 중요한 대화형 앱에 맞습니다.

https://x.com/googleaidevs/status/2039782721460027676

#geminiapi #inference #pricing #api #ai

Google AI Developers (@googleaidevs) on X

Balance cost & reliability with our new Flex & Priority inference tiers in the Gemini API! Flex: Pay 50% less for cost-sensitive & latency-tolerant workloads Priority: Highest reliability for your most critical, interactive apps (with premium pricing) Together with the async

X (formerly Twitter)
AI SparkupMar 18

Gemini API 비용 관리, 이제 직접 한도를 설정할 수 있습니다

Google이 Gemini API에 프로젝트별 월 지출 한도 설정과 자동 티어 업그레이드 기능을 공개했습니다. AI 앱 비용 관리가 쉬워집니다.

https://aisparkup.com/posts/10280