NathanRoll commited on
Commit
ffa186b
路
verified 路
1 Parent(s): de5d8c3

Add the Hosted API section (English, 60 s, 4 MiB, no word timestamps, plan allowance)

Browse files

Discloses the hosted preview's limits from the oruk.ai OpenAPI contract and what hosted adds over the local weights (no install or GPU, optional emotion scores and speaker diarization). Links carry utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet. Everything else on the card is unchanged.

Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -221,6 +221,10 @@ Q8 and F16 pass real transcription and protocol checks on Apple silicon with Met
221
 
222
  [Artifact catalog](https://github.com/Oruk-AI/orukeet/blob/main/src/orukeet/artifacts.json) 路 [Native conversion and validation](https://github.com/Oruk-AI/orukeet/tree/main/evidence/r3-promotion-20260908/)
223
 
 
 
 
 
224
  ## Questions and bugs
225
 
226
  Reproducible transcription or runtime bugs go to [GitHub issues](https://github.com/Oruk-AI/orukeet/issues/new/choose); include the model SHA-256, OS/architecture, runtime/device and input format. Model-level questions (languages, accuracy, fine-tuning, licensing, packaging Orukeet in an app) go to [GitHub Discussions](https://github.com/Oruk-AI/orukeet/discussions). Orukeet detects the language itself: the weights and the native API have no language-forcing or vocabulary-biasing input, and the native response returns `language: null`. Hosted Orukeet on oruk.ai transcribes English only. Security reports: [SECURITY.md](https://github.com/Oruk-AI/orukeet/blob/main/SECURITY.md).
 
221
 
222
  [Artifact catalog](https://github.com/Oruk-AI/orukeet/blob/main/src/orukeet/artifacts.json) 路 [Native conversion and validation](https://github.com/Oruk-AI/orukeet/tree/main/evidence/r3-promotion-20260908/)
223
 
224
+ ## Hosted API
225
+
226
+ Oruk also serves Orukeet as a hosted English transcription endpoint (preview) at [oruk.ai/models/orukeet](https://oruk.ai/models/orukeet?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet); it needs an Oruk API key. Limits per the [OpenAPI contract](https://oruk.ai/openapi.json?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet): English only; at most 60 seconds of audio per request; 4 MiB for the complete multipart request; no word timestamps (speaker-turn times only when diarization is enabled); usage draws from the plan's separate Orukeet allowance at $0.027 per audio hour. Hosted adds no install or GPU, plus optional emotion scores and speaker diarization on the same request. The local, open-weights path covers 25 languages and runs offline.
227
+
228
  ## Questions and bugs
229
 
230
  Reproducible transcription or runtime bugs go to [GitHub issues](https://github.com/Oruk-AI/orukeet/issues/new/choose); include the model SHA-256, OS/architecture, runtime/device and input format. Model-level questions (languages, accuracy, fine-tuning, licensing, packaging Orukeet in an app) go to [GitHub Discussions](https://github.com/Oruk-AI/orukeet/discussions). Orukeet detects the language itself: the weights and the native API have no language-forcing or vocabulary-biasing input, and the native response returns `language: null`. Hosted Orukeet on oruk.ai transcribes English only. Security reports: [SECURITY.md](https://github.com/Oruk-AI/orukeet/blob/main/SECURITY.md).