
Cekura tech stack
Automated QA for Voice AI and Chat AI agents
Vibe coding
“Skills to design and optimize metrics easily - Can refer to skills here: https://github.com/cekura-ai/cla...” — the maker, Sep 2026 ↗
AI models and media
“We use Claude models for parts of automated scenario generation, evaluation and building some of our pre-defined metrics” — the maker, Sep 2026 ↗
“We use OpenAI models for parts of automated scenario generation, evaluation and building some of our pre-defined metrics” — the maker, Sep 2026 ↗
“Used in some of the pre-defined metrics and metric optimizer” — the maker, Sep 2026 ↗
“Realtime API is the best model, providing intelligence on audio.” — the maker, Sep 2026 ↗
“We use Deepgram for STT. It is still one of the best for transcription of RealTime AI” — the maker, Sep 2026 ↗
“We use ElevenLabs to create natural AI voices in any language. ElevenLabs also provide the best voice quality, including clones of real-world personalities” — the maker, Sep 2026 ↗
“Cartesia is the best TTS model in terms of latency. Many of our clients use Cartesia to solve their latency issues” — the maker, Sep 2026 ↗
Agent building blocks
Ship and run
Cekura next to products in LLM and AI agent observability
- Hosting46% of 24 pick
Vercel — so does Cekura - LLM API75% of 12 pick
OpenAI API — so does Cekura - Database45% of 11 pick
Supabase — so does Cekura - Frontend Framework80% of 10 pick
Next.js — so does Cekura
Built on a similar stack
Products that share the most distinctive building blocks with Cekura.