Agent Builder by AirtopWeb agents that heal themselves.
Promoted
One API for speech-to-text, language models, and text-to-speech, with public benchmarks beside runtime availability.
What's great
Been burned by exactly the problem this solves - manually testing voice models against a handful of sample clips every time a new one drops, then forgetting to re-test six months later when something better shipped. Having routing decided against real public benchmarks instead of vendor marketing numbers is the actual value here, not just "one API for everything."
What needs improvement
Would like to see the benchmark methodology published somewhere permanent rather than just referenced in a launch post - if the whole pitch is "trust our ranking, not vendor marketing," the scoring process itself needs to be as transparent and auditable as the results.
vs Alternatives
Looked at ElevenLabs and Deepgram directly but those are single vendors, not routers - I'd still have to run my own comparison across them for each language. Speko's pitch of ranking by actual public benchmark per language is a different category of tool, not a competitor to either.
Ratings
Ease of use
Reliability
Value for money
Customization
Report
38 views
Speko
@abdikbek Very interesting product. All the best!
I’ve already discussed this direction with Bek, and we even hosted a deep-dive online meetup together about the development of voice AI.
That’s why it’s especially interesting to see how the idea behind Speko is now evolving into a real product. Choosing the right voice stack is becoming increasingly complex as new models and providers keep emerging.
I really like Speko’s approach: independent benchmarks, routing based on the specific use case and language, and no bias toward their own models.
Very interesting product and direction. Good luck to Bek and the Speko team!
Speko
@umedrahimoff Thank you a lot Umed aka, enjoyed the interview!
Congratulations on the launch @abdikbek! All of us needed a voice AI OpenRouter for sure. Wondering how often you would refresh this list of APIs or include more providers.
What are the advantages compared to Google’s open-source libraries and other alternatives? Also, what about less commonly supported languages like Swedish or Danish?
P.S. I just saw a post here about a kids’ app. You should consider partnering with them - they have voice recognition for children and convert speech to text.
Looks good, but would be nice if the site provided also actual voice samples of each model, e.g. just same text with type of voice prompt benchmarked accross different models.
SUN
Love your product, guys. We are using it at SUN
Macaly
openrouter for voice is such a usefull idea 🎙️ which stt is winning rn?