Href Https
general · 2 signals · 1 source
Evidence
Show HN: eBook to audiobook narration with realistic AI voices — For a while I've wanted to try out the new AI voices for long-form narration, but everything I found required a subscription that didn't justify my limited usage. I came across the open Kokoro model [0] and the voices are very good -- good enough to listen to for hours without the fatigue I got from legacy, robotic TTS voices. The model is 82m parameters and designed to run fast, but I still struggled to get reasonable times from CPU inference on my 12-core laptop. I thought a cloud-based GPU service would let me generate audiobooks fast enough to feed my own self-hosted library, and that same pipeline could become a product other people could use.<p>I had two goals in building this: get some exposure to AI multi-agent coding workflows, and build a TTS product targeting ebook to audiobook conversion specifically. 99% of ebookaloud was written by DeepSeek v4 in OpenCode. I've used about 750 million tokens costing $12 in credits over the course of a month, and I'm very pleased with the results. Every change/feature went through a plan -> implement -> test -> review -> correct -> commit cycle with a mix of Pro and Flash agents. This was generally limited to one or two concurrent workers. I had a separate eval agent for quality control on various parts of the extraction and synthesis pipeline, which I could run 8-10 at a time. I may be approaching Yegge's Stage 6 [1] in terms of AI workflow automation.<p>I later set up Claude Code and ran Opus 4.8 side by side with DeepSeek. There are definitely quality differences, but I'm an experienced developer with a hands-on approach. I didn't write any of the code, but I have read critical sections of what it generated and had extensive conversations with DS Pro about each step of the approach. Opus didn't have much critical to say about DeepSeek's choices, and I'm not convinced a frontier model would have made an appreciable difference for my workflow. I suspect on a large codebase the differences would become more apparent, but the few changes I implemented with Opus had similar issues to all the models I've used: random changes without my direction, over-complicating simple solutions, taking unanticipated/destructive actions when it gets stuck, etc. I do see Opus being capable of handling more of the complex planning and orchestration that I was involved in. That's something I may want sometimes but not others.<p>As to the product itself, there are a lot more sophisticated solutions out there. I'm not trying to compete with ElevenLabs. I'm targeting m4b generation for a seamless audiobook experience with a pay-as-you-go pricing model and good-enough output quality. This is the first product I've ever tried to commercialize, and AI code generation put something polished within reach. Without AI, this would have taken me 6-8 months of manual research and development, and I would have gotten burned out long before completing it.<p>I have a free sample on the front page of the site if you just want to see what it generates in terms of voice/format. I made a few opinionated decisions regarding output quality. I aimed for 140 wpm for most of the voices to match industry standards, but some are much slower or faster and lose prosody at that rate. Rather than give users a wall of options, I'm deferring to the playback device for things like speed control. If the site sees real usage I'd like to expand to support Kokoro's other languages, and extraction and synthesis from PDF would round out the product quite a bit.<p>[0] <a href="https://github.com/hexgrad/kokoro" rel="nofollow">https://github.com/hexgrad/kokoro</a><p>[1] <a href="https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16dd04#b356" rel="nofollow">https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16d...</a>
Show HN: Turn native language audio into flashcards and shadowing practice — Here is a tool I built initially for myself to help with my German and Greek language studies. It started as a hack for creating Anki cards from native language audio. It extracts the words, finds their base forms (lemmas) and groups the examples by the lemma. At some point I realised that I have a transcription with word level timestamps that opens a lot of other opportunities. So I added a mode to click the first and last word in the transcript and it starts looping with the right gap and repeat count.<p>Another feature I use a lot is selecting an audio fragment, sending a predefined prompt to an AI to "explain grammar" or "explain nuances of meaning" and I still experimenting with prompts.<p>And because shadowing is so easy I also use it as a player to improve my English pronunciation. (I am not a native English speaker.)<p>I made a quick video showing the workflow for creating Anki cards and shadowing: <a href="https://youtu.be/TaR58uuDBvU?si=o5aGLAi2S-BZ7Zy9" rel="nofollow">https://youtu.be/TaR58uuDBvU?si=o5aGLAi2S-BZ7Zy9</a><p>The app supports 15 input languages (Japanese and Chinese are the latest experimental additions), and more than 30 output languages.<p>I would really appreciate it if you could try it <a href="https://lingochunk.com/try" rel="nofollow">https://lingochunk.com/try</a>. I know there are other tools with similar functionality but I created something that fits my workflow and it is fun to build.<p>Also I struggled to find public domain audio for the try page. I'd be grateful if anyone could point me to public domain sources (I used LibriVox, Wikimedia and FSI courses), or if you're a creator, let me feature some of your own recordings with credits and links.