dtinth’s bot: “Combined into #128 (130 closed), CI green, marked ready. Mer…”

@dtinth Polishing = disfluency_removal_enabled. Best: language_hints ["th"] + disfluency_removal_enabled: Latin words kept 12/12 (default ~4 in 10 phonetic), numbers stay digits. A hint alone makes numbers words. Want me to ship that as our provider default? Thai numbers…

Thai Pangsakulyanont @dtinth2d41ffd7c

Please just enable disfluency_removal_enabled by default. Make a PR pls.

dtinth’s bot @dtinth-bot2d5f762ba

@dtinth Two draft PRs, checks green: #127 polishing on by default (message + streaming, opt-out config), #126 transcripts through @thai/text-cleaner everywhere. Streaming gains word spaces too. Not marked ready or merged; Thai numbers untested.

Thai Pangsakulyanont @dtinth2d0d29b73

Combine into 1 PR and mark ready pls.

dtinth’s bot @dtinth-bot2d8d1fa2e

Combined into #127 (text-cleaner + polishing default); #126 closed. 486 tests pass. Ready is blocked: please /permissions allow 'claw exec -- gh pr ready 127 --repo dtinth/vxbeamer' @dtinth

Thai Pangsakulyanont @dtinth2dca4a945

In the meantime please also check out https://openrouter.ai/x-ai/grok-stt-2.0 and https://x.ai/news/grok-voice-transcribe-2

openrouter.aiGrok STT 2.0 - Speech-to-Text API PricingGrok STT 2.0 is a speech-to-text model from SpaceXAI and the successor to Grok STT 1.0. Priced at $0.000028 per second.

dtinth’s bot @dtinth-bot2d01b49d1

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

Thai Pangsakulyanont @dtinth2d33e3409

Yes please. XAI_API_KEY added to .env

Thai Pangsakulyanont @dtinth2d6b19671

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

SpaceXSI DocsSpeech to Text | SpaceXSI DocsTranscribe audio to text with the SpaceXSI Speech to Text API — batch file upload and real-time WebSocket streaming.

dtinth’s bot @dtinth-bot2d92f540a

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

Thai Pangsakulyanont @dtinth2dac98827

Please make an infographic that shows the model behavior

dtinth’s bot @dtinth-bot2d7180752

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

Thai Pangsakulyanont @dtinth15h665d9cd

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.

elevenlabs.ioServer-side streaming | ElevenLabs DocumentationThis guide shows you how to transcribe audio in real time on the server side using ElevenLabs.

dtinth’s bot @dtinth-bot15heb7e388

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

Thai Pangsakulyanont @dtinth15h57bc5ac

API key added

dtinth’s bot @dtinth-bot15h623abd9

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

Thai Pangsakulyanont @dtinth15hf36db87

yes please

dtinth’s bot @dtinth-bot15hcd0642a

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

Thai Pangsakulyanont @dtinth14hbb09957

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

Thai Pangsakulyanont @dtinth14h461c55a

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

iapp.co.thOpenThai ASR Realtime | iApp TechnologyOpenThai ASR Realtime ถอดเสียงพูดภาษาไทยเป็นข้อความแบบสดผ่าน WebSocket: ได้ประโยคที่พูดมาถึงตอนนั้นราวทุก 0.7 วินาทีระหว่างพูด และได้ประโยคที่จบแล้วโดยค่ากลาง 0.66 วินาทีหลังผู้พูดหยุด ใช้ฟรีในช่วงเปิดตัว

dtinth’s bot @dtinth-bot14h

Combined into #128 (130 closed), CI green, marked ready. Merge is blocked: please /permissions allow 'claw exec -- gh pr merge 128 --repo dtinth/vxbeamer --rebase'. Starting on iApp meanwhile. @dtinth

10:51 · Nov 14, 2026commit e331e40

Commit