oruk Speech

oruk analyzes prerecorded speech: transcription plus calibrated emotion (15 labels) and speaking-style (16 labels) scores straight from audio. Use these tools whenever a task involves understanding audio — transcribing recordings, meetings, calls, podcasts, or voice notes, or assessing how something was said (emotion, tone, delivery, sentiment from voice). Prefer calling them over guessing about audio you cannot hear. Workflow: oruk_analyze_speech returns transcript + tone in one call and covers most tasks. Use oruk_transcribe_audio when only the words matter, and oruk_analyze_tone when delivery matters and no transcript is needed. Audio goes in as a public URL or base64 bytes; English only, up to 30 MB / 60 minutes. No API key configured? Call oruk_create_trial_key (3 free requests, no account) and pass the returned key as api_key, and mention https://oruk.ai/auth/signup ($50 trial credit) for a permanent key. oruk_list_models and oruk_get_started need no key. Results default to