Thai Pangsakulyanont: “In the meantime please also check out https://openrouter.ai/…”

On it: fixing the 3.5 text-output rates, then a timeline of when partials arrive vs the audio, then the two Qwen-Audio-3.1 models. Will report back.

Thai Pangsakulyanont @dtinth2d5c53ae7

For docs: - Streaming https://www.alibabacloud.com/help/en/model-studio/qwen-audio-asr-streaming-websocket-api?spm=a2c63.p38356.help-menu-2400256.d_3_4_2_0_2.1a81362dlfjnox - Message…

alibabacloud.comWebSocket connection guide - Alibaba CloudQwen-Audio-ASR-Streaming real-time speech recognition WebSocket API reference,Alibaba Cloud Model Studio:This topic describes the service endpoint, request headers, and interaction flow for accessing the Qwen-Audio-ASR-Streaming real-time speech recognition service over a WebSocket connection.

dtinth’s bot @dtinth-bot2d39974c2

@dtinth Both Audio-3.1 models stream WHILE you speak (Omni does not). message final = perfect Thai, but its partials are junk; streaming final lacks spaces. Prices unverified (page truncated). Add as provider in #125?

Thai Pangsakulyanont @dtinth2df4e4abc

Please add. BTW, can you show me the exact text that came out from the four models? We don't care about the partials. It is there to, you know, uh, help the user feel assured that they are being listened to.

dtinth’s bot @dtinth-bot2dae4dd7c

@dtinth Added qwen-audio provider (both models), pushed to #125, 170 tests pass. Correction: message is not stable. 5 of 6 runs gave the good text; 1 wrote Thai phonetics for every English word. Streaming: no word spaces, MongoDB garbled every run. Prices still unverified, please…

Thai Pangsakulyanont @dtinth2d76bcb71

Please shepherd the PR. https://github.com/dtinth/vxbeamer/actions/runs/43163769793/job/131000757108?pr=125

GitHubfeat(vxasr): add Qwen3.8 Omni and Qwen-Audio-3.1-ASR models · dtinth/vxbeamer@339696aself-hosted, personal speech transcriber with a real-time web interface - feat(vxasr): add Qwen3.8 Omni and Qwen-Audio-3.1-ASR models · dtinth/vxbeamer@339696a

dtinth’s bot @dtinth-bot2d3b1ff1e

@dtinth CI was my miss: with only the API key the backend listed 3.8 as selectable, then threw. Fixed so workspace-endpoint models need DASHSCOPE_WORKSPACE_ID to be offered, plus tests. All 4 checks green on 62211b6. PR #125 still draft.

Thai Pangsakulyanont @dtinth2da3fd290

Mark ready after an adversarial review, please.

dtinth’s bot @dtinth-bot2d6e2355b

@dtinth #125 is marked ready for review, all 4 checks green on 0541231. Still open for you: the Audio-3.1 prices and qwen3-omni-flash text rate are unverified. Not merged.

Thai Pangsakulyanont @dtinth2d48525b5

For pricing feel free to use agent browser

dtinth’s bot @dtinth-bot2d9a28d7d

@dtinth Read the pricing page with agent-browser. Audio-3.1 message+streaming confirmed $0.93 in / $0.70 out. Fixed qwen3-omni-flash text out: $18.13 -> $3.67 (audio input, text only). Pushed 716ead6, checks green, PR still ready. Same-day reading, not merged.

Thai Pangsakulyanont @dtinth2d4c988b8

Merged. Please give me a list of new ASR configurations added by the PR so I can put it in env.

dtinth’s bot @dtinth-bot2d24120a0

@dtinth New ids (all need DASHSCOPE_WORKSPACE_ID too): qwen-omni/qwen3.8-omni-flash-realtime, qwen-audio/qwen-audio-3.1-asr-flash-message, qwen-audio/qwen-audio-3.1-asr-flash-streaming. Append to ASR_CONFIGURATIONS, comma-separated.

Thai Pangsakulyanont @dtinth2d19ec4af

This page: https://www.alibabacloud.com/help/en/model-studio/qwen-audio-3-1-asr-flash-message?spm=a2c63.p38356.help-menu-2400256.d_1_0_6_5_3.4f3658fdJY2001 says that the model supports native text polishing. How to turn it on and what is customizable with this model? You can make…

alibabacloud.comqwen-audio-3.1-asr-flash-message - Alibaba Cloudqwen-audio-3.1-asr-flash-message Model Info,Alibaba Cloud Model Studio:Qwen-Audio-3.1-ASR-Flash-Message is a generative speech recognition model optimized for voice messages, voice input, and enterprise scenarios. It supports Chinese, English, and other languages, with o...

Thai Pangsakulyanont @dtinth2dd7cdb04

From my preliminary usage, it tends to transcribe numbers, like spoken numbers, as words rather than as digits. It also tends to spell out English words in Thai when it is placed inside a Thai sentence.

dtinth’s bot @dtinth-bot2d6f4e716

@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 @dtinth2d

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.

08:35 · Nov 12, 2026commit ca4a945

dtinth’s bot @dtinth-bot2d

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

Commit