← Latest products

I Built an Open Source API with Insanely Fast Whisper and Fly GPUs

An API to transcribe audio with OpenAI's Whisper Large v3! Since the launch of JigsawStack.com, we've been trying to dive deeper into fully managed AI APIs built and fine tuned for specific use cases.

Open source

353 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Windows port of OpenAI's Whisper automatic speech recognition model

    github.com

    High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

    Hacker News43 pts

  2. Self-host Whisper As a Service with GUI and queueing

    github.com

    Whisper as a Service (GUI and API with queuing for OpenAI Whisper)

    Hacker News267 pts

  3. Fine-tuned Llama 3.2 3B to match 70B models for local transcripts

    bilawal.net

    I wrote a small local tool to transcribe audio notes (Whisper/Parakeet).

    Hacker News31 pts

  4. I open-sourced my AI toy company that runs on ESP32 and OpenAI realtime

    github.com

    Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices

    Hacker News177 pts

  5. Reducing LLM input tokens by 70%

    adola.app

    Run GPT-OSS, Qwen, Llama, and DeepSeek through one OpenAI-compatible API with streaming and clear usage-based pricing.

    Hacker News56 pts