Commit

Read both. Grok STT 2.0: $0.10/h batch, $0.20/h streaming (OpenRouter $0.000028/s=$0.10/h), word timestamps, key terms (100), filler removal, 19+ langs, auto language. No xAI provider in vxasr yet. Want me to add one (streaming) + test Thai? Need XAI_API_KEY @dtinth

Yes please. XAI_API_KEY added to .env

I think text formatting should be enabled. re https://docs.x.ai/developers/model-capabilities/audio/speech-to-text…

Draft PR #128: xai/grok-voice-transcribe-2.0, partials ~1s, $0.20/h. Formatting on (needs language, Thai unsupported, so en; Thai numbers untested). Server stalls 10-40s sometimes. @dtinth

Please make an infographic that shows the model behavior

Grok infographic: partials from ~1s, text self-corrects, final is the utterance event, end wait stalls 10-40s sometimes, formatting only helps with en. @dtinth

I want to try out Scribe Realtime v2. https://elevenlabs.io/docs/eleven-api/guides/how-to/speech-to-text/realtime/server-side-streaming… Want to see similar infographic. Also want to know whether it supports faster than realtime dumping.

On it. No ElevenLabs key in .env yet: please add ELEVENLABS_API_KEY. Reading the docs for the model id, pricing and speed meanwhile. @dtinth

API key added

Scribe v2 Realtime: yes, faster-than-realtime dump works (9s in 1.6s, 37s in 2.7s, same text). 2.2s to first partial, 0.3s commit-to-final, $0.22/h. Add a provider (draft PR)? @dtinth

yes please

Draft PR #130: elevenlabs/scribe_v2_realtime, fast-dump capable, 500 tests pass. Handles 0.3s commit minimum + vendor auto-commit race. Conflicts with #128 on lists. @dtinth

Please combine 128 and 130 into a single PR, shepherd to green, then merge.

After that, I want to test this: https://iapp.co.th/docs/speech/speech-to-text/realtime…

#128 merged (rebase) into main: xai Grok + ElevenLabs Scribe v2 providers, CI was green. Still need IAPP_API_KEY in .env to start the iApp realtime test. @dtinth

IAPP_API_KEY added

iApp realtime tested live. Fast dump works (9 s in 1.7 s, 37 s in 2.5 s), but >120 s backlog gives TOO_FAST. English words come out in Thai script, English speech is garbage. Free for now. 3rd parallel session got 429. Want a provider? @dtinth

Yes, piggyback into that PR please.

Draft PR #132: iapp provider, fast dump paced past the 120 s TOO_FAST limit (298 s clip ran fine). Correction: latency_ms 80 changed spellings, so default stays 560. Waiting on CI. @dtinth

#132 CI all green (Check and Test, e2e, Vercel). Still a draft; say the word and I'll mark it ready. @dtinth