HN

Comments (48)

• Menu

  webo
  The benchmarks page seems interesting and something I can use to help make an informed decision. Can you talk about how you're measuring some of these? I imagine it needs to involve some human input.https://benchmarks.speko.ai/turntaking
• Menu

  spmartin823
  Does this include a turn taking API? It'd be great to have one API that could do "Conversation in a box". One of the biggest annoyances is daisy chaining many models together for turn taking, dumb models for immediate responses, with smarter models returning and taking over after.
• Menu

  MikhailTal
  What is the difference with Livekit Gateway? https://livekit.com/blog/introducing-livekit-inferenceOr even something more managed like Vapi?
• Menu

  maho
  Which model best allows me to transcribe speech that uses a lot of domain-specific terms? For example, when I say "Claude Code", it often gets transcribed as "Cloud Code", and I have to go back and edit or do a second pass with a traditional LLM (which can introduce additional errors).
• Menu

  bewareofscams
  Seems to be useless, the state of art for all categories is local on-device, voice model vendors are just rent seekers for those who know no better.
• Menu

  cjjuice
  I made a completely free 100% on device translation app https://apps.apple.com/us/app/arda-translate/id6778970560 and hard to image a world where TTS and STT will not be done locally in the future
• Menu

  Tepix
  Ever since OpenAI launched their improved voice mode, I've been looking for a capable LLM with builtin voice-in and -out. Llama 4 was supposed to be it but turned out to be a dud. I haven't followed the topic closely lately, did I miss anything? Are there capable (!) open weights omni models that allow low latency voice chat? If so, what software do you use them with? Can you use a PWA on your phone? WebRTC? WebTransport?
• Menu

  cnqso
  What does WER/CER stand for? I see it as some kind of key metric under each model but not clear what it's measuring
• Menu

  dayvough
  Looks awesome, can't wait to try it for some Filipino workflows when it's available!
• Menu

  dhruv3006
  the concept is interesting I must say - good luck !
• anon
  undefined
• Menu

  IgorBlink
  any progress with on-device models??
• Menu

  narrationbox
  > Typical production voice agent is an ensemble of three models: STT, an LLM, and TTS.To use a claudism, I would like to push back on this. The industry is very much moving towards one-model-does-all end to end trained similar to LLMs and VLMs. Mostly for latency reasons and partially because the results for the end to end trained models are just so much better than those using three pieces architectures.I think most of the value prop is in automatic evals, not routing specifically. A better pitch for you would be "the LM Arena of voice models" rather than comparing yourself to openrouter because the value add is rather questionable. For TTS specifically, the current SOTA for production systems are all using prompt based voice gen i.e. instead of having 10 different Tacotron models trained on 10 different models, these days it's all a single large model and the "style" is a prompt in the system prompt. The input is usually something like <System prompt> Speak in a deep smooth voice similar to a documentary narrator </System prompt> <Text to Narrate> Speko is the ultimate evaluation platform for voice agents. We do automatic evals. </Text to Narrate> It's the same for voice cloning too, you just pass the reference speech as an input file for all generations. A lot of systems don't have any separate style vector extraction step or model-specific fine-tuning anymore.So something like OpenRouter for voices offer questionable value given that stakeholders usually make this sort of decisions once at the start of the project. On the other hand if you can offer automatic evals and figure out which prompts give the most similar results across different voice providers, that would offer a lot more value. It would be nice to be able to switch from e.g. Grok voice agents to ChatGPT voice agents knowing that the output style won't change too much. There are many companies now with evals as a core business model: LM Arena, Artificial Analysis, Prompt foo (before they got acquired and pivoted to security only) so many take a look at them.Source: we have been building TTS systems for over a decade too https://narrationbox.com
• Menu

  yujonglee
  cool! we have something similar implemented: https://github.com/fastrepl/anarlog/tree/main/crates/owhispe...
• Menu

  greyb
  The link, since it seems to be missing?https://speko.ai/