{"object":"list","pricing_version":"2026-07-11","pricing_basis":"legacy_metered_reference","pricing_note":"Legacy per-task rates, add-ons, and volume discounts are reference fields, not subscription invoice prices. Plans cover the speech model lineup. New organizations need separate approval for Resonance 2; an active trial or plan does not by itself grant access. Hobby is $9/month, Builder $49/month, and Production $199/month. Spectra-2, Resonance 1, Resonance 2, Fourier, Realtime, and Proficiency share 250, 2,500, or 20,000 monthly audio minutes, respectively, including supported diarization. Each plan also includes a separate Orukeet allowance, starting at up to 20,000 transcription minutes on Hobby. Orukeet uses $0.00045/minute ($0.027/hour); optional tasks draw from its allowance at their published rates. Both subscription allowances reset monthly, including on annual plans. Other-model audio uses a one-second minimum. Orukeet measures actual duration and rounds each request to one microdollar. Optional tasks use its allowance; excess usage is billed monthly within the shared spending cap. Usage cost fields show consumption, not the final invoice.","pricing_url":"https://oruk.ai/pricing","subscription_terms_reviewed_on":"2026-09-13","subscription_plans":[{"id":"hobby","name":"Hobby","monthly_usd":9,"included_audio_minutes":250,"overage_usd_per_audio_minute":0.02,"included_orukeet_allowance_microusd":9000000,"estimated_orukeet_transcription_minutes":20000},{"id":"builder","name":"Builder","monthly_usd":49,"included_audio_minutes":2500,"overage_usd_per_audio_minute":0.015,"included_orukeet_allowance_microusd":49000000,"estimated_orukeet_transcription_minutes":108888},{"id":"production","name":"Production","monthly_usd":199,"included_audio_minutes":20000,"overage_usd_per_audio_minute":0.012,"included_orukeet_allowance_microusd":199000000,"estimated_orukeet_transcription_minutes":442222}],"subscription_terms":{"shared_audio_minute_models":["oruk-spectra-2","oruk-resonance-2","oruk-resonance","oruk-fourier","oruk-realtime","oruk-proficiency-1"],"supported_diarization_included_in_shared_minutes":true,"allowance_reset":"monthly","annual_base_fee_discount_percent":20,"trial":{"days":7,"card_required":true,"charge_today_usd":0,"allowance_fraction":0.25,"overage_enabled":false},"orukeet":{"billing_basis":"separate_subscription_allowance","optional_tasks_consume_same_allowance":true,"request_rounding_microusd":1,"transcription_minutes_are_estimates":true},"extra_usage":"Both allowances share one monthly spending cap; initially the monthly base fee or discounted monthly equivalent.","existing_prepaid_credits":"Existing balances retain their original terms."},"data":[{"id":"oruk-spectra-2","name":"oruk Spectra-2","created":1782604800,"description":"Multilingual transcription with 15 emotion and 16 speaking-style scores for the whole recording. Uses shared speech understanding plan minutes.","lifecycle":"Stable","input_modalities":["audio"],"output_modalities":["text"],"languages":["bg","hr","cs","da","nl","en","et","fi","fr","de","el","hu","it","lv","lt","mt","pl","pt","ro","ru","sk","sl","es","sv","uk"],"max_audio_seconds":60,"max_file_bytes":4194304,"supported_sampling_parameters":[],"supported_features":["transcription","emotion","style","clip_scores"],"pricing_basis":"subscription","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0002","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"transcription":"0.0080","analysis":"0.0120"},"is_ready":true,"availability":"production","language_detection":"automatic","language_details":[{"code":"bg","name":"Bulgarian"},{"code":"hr","name":"Croatian"},{"code":"cs","name":"Czech"},{"code":"da","name":"Danish"},{"code":"nl","name":"Dutch"},{"code":"en","name":"English"},{"code":"et","name":"Estonian"},{"code":"fi","name":"Finnish"},{"code":"fr","name":"French"},{"code":"de","name":"German"},{"code":"el","name":"Greek"},{"code":"hu","name":"Hungarian"},{"code":"it","name":"Italian"},{"code":"lv","name":"Latvian"},{"code":"lt","name":"Lithuanian"},{"code":"mt","name":"Maltese"},{"code":"pl","name":"Polish"},{"code":"pt","name":"Portuguese"},{"code":"ro","name":"Romanian"},{"code":"ru","name":"Russian"},{"code":"sk","name":"Slovak"},{"code":"sl","name":"Slovenian"},{"code":"es","name":"Spanish"},{"code":"sv","name":"Swedish"},{"code":"uk","name":"Ukrainian"}],"supported_tasks":["transcription","analysis"],"endpoints":{"analysis":"/v1/audio/analysis","transcription":"/v1/audio/transcriptions"},"min_audio_seconds":0.045,"max_multipart_bytes":4210688,"sample_rate":16000,"channels":1,"formats":["wav","flac","pcm16","float32le"],"score_scope":"clip","emotion_labels":15,"style_labels":16,"subscription_allowance":"shared_audio_minutes","docs":"https://oruk.ai/docs#spectra-2","is_free":false},{"id":"oruk-resonance-2","name":"oruk Resonance 2","created":1782604800,"description":"Emotion and speaking-style classification with 31 continuous scores and six signed opposite pairs. Same plans and affect pricing as Resonance 1.","lifecycle":"Preview","input_modalities":["audio"],"output_modalities":["text"],"languages":[],"max_audio_seconds":120,"max_file_bytes":31457280,"supported_sampling_parameters":[],"supported_features":["emotion","style","signed_axes","pcm_streaming"],"pricing_basis":"legacy_metered_reference","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0001666667","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"affect":"0.0100"},"is_ready":true,"approval_required":true,"access_status_endpoint":"/v1/models/oruk-resonance-2/access","request_access_url":"https://oruk.ai/account/model-access","endpoint":"/v1/audio/resonance-2","stream_endpoint":"/v1/audio/resonance-2/stream","streaming":{"transport":"websocket","authentication":"bearer_header","encoding":"float32le","sample_rate":16000,"channels":1,"max_frame_bytes":64000,"max_buffered_audio_seconds":120,"commit_mode":"explicit_sample_range","min_commit_audio_seconds":0.1,"max_commit_audio_seconds":120,"regimes":["f1","precision"],"result_object":"speech.affect.result","idempotency":"shared_http_ws","docs":"https://oruk.ai/docs#resonance-2-streaming"},"supported_tasks":["affect"],"availability":"preview","language_note":"No language code required; accuracy varies by language.","subscription_allowance":"shared_audio_minutes","is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"oruk-orukeet","name":"oruk Orukeet","created":1782604800,"description":"Fast English transcription with optional emotion detection and speaker diarization; subscription task pricing","lifecycle":"Preview","input_modalities":["audio"],"output_modalities":["text"],"languages":["en"],"max_audio_seconds":60,"max_file_bytes":4194304,"supported_sampling_parameters":[],"supported_features":["pcm_streaming","emotion_detection","diarization"],"pricing_basis":"subscription","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0000075","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"transcription":"0.00045","emotion_detection":"0.0080","diarize":"0.0040"},"is_ready":true,"available_tasks":{"emotion_detection":true,"diarize":true},"is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"oruk-resonance","name":"oruk Resonance 1","created":1782604800,"description":"Flagship speech recognition model: English transcription, 15 emotion labels, 16 speaking-style labels, and timed analysis. The default for file analysis.","lifecycle":"Stable","input_modalities":["audio"],"output_modalities":["text"],"languages":["en"],"max_audio_seconds":3600,"max_file_bytes":31457280,"supported_sampling_parameters":[],"supported_features":[],"pricing_basis":"legacy_metered_reference","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0002","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"transcription":"0.0080","emotion":"0.0080","style":"0.0080","affect":"0.0100","analysis":"0.0120"},"is_ready":true,"is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"oruk-fourier","name":"oruk Fourier","created":1782604800,"description":"English transcription and native 15-label emotion analysis in parallel. The API also returns 16 speaking-style labels through the shared style model.","lifecycle":"Stable","input_modalities":["audio"],"output_modalities":["text"],"languages":["en"],"max_audio_seconds":3600,"max_file_bytes":31457280,"supported_sampling_parameters":[],"supported_features":[],"pricing_basis":"legacy_metered_reference","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0002","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"transcription":"0.0080","emotion":"0.0080","style":"0.0080","affect":"0.0100","analysis":"0.0120"},"is_ready":true,"is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"oruk-realtime","name":"oruk realtime","created":1782604800,"description":"Live transcription in 32 locales, with automatic language detection and a separate stream of phrase-level emotion scores. Speaking-style analysis uses the English file API.","lifecycle":"Preview","input_modalities":["audio"],"output_modalities":["text"],"languages":["en-US","en-GB","es-US","es-ES","fr-FR","fr-CA","it-IT","pt-BR","pt-PT","nl-NL","de-DE","tr-TR","ru-RU","ar-AR","hi-IN","ja-JP","ko-KR","vi-VN","uk-UA","pl-PL","sv-SE","cs-CZ","nb-NO","da-DK","bg-BG","fi-FI","hr-HR","sk-SK","zh-CN","hu-HU","ro-RO","et-EE"],"max_audio_seconds":600,"max_file_bytes":null,"supported_sampling_parameters":[],"supported_features":["streaming","phrase_emotions","automatic_language_detection","punctuation","word_timestamps"],"pricing_basis":"legacy_metered_reference","pricing":{"prompt":"0","completion":"0","request":"0","image":"0","audio":"0.0001333333","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":{"realtime_transcription":"0.0080"},"is_ready":true,"is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"oruk-proficiency-1","name":"oruk Proficiency","created":1782604800,"description":"Word and recording pronunciation scores on 0–1, with the original CEFR and fluency fields","lifecycle":"Preview","input_modalities":["audio"],"output_modalities":["text"],"languages":["en"],"max_audio_seconds":3600,"max_file_bytes":31457280,"supported_sampling_parameters":[],"supported_features":[],"pricing_basis":"legacy_metered_reference","pricing":{"prompt":"0","completion":"0","request":"0.03","image":"0","audio":"0","input_cache_read":"0"},"per_task_pricing_usd_per_audio_minute":null,"is_ready":true,"is_free":false,"datacenters":[{"country_code":"US"}]},{"id":"orukzero","name":"OrukZero","description":"English synthetic speech detection with clip and segment scores. Included at no additional charge with any active paid Oruk plan.","lifecycle":"Preview","input_modalities":["audio"],"output_modalities":["text"],"languages":["en"],"min_audio_seconds":1,"max_audio_seconds":60,"max_file_bytes":12582912,"channels":[1,2],"formats":["wav","flac","ogg","mp3"],"supported_features":["synthetic_speech_detection","segment_scores"],"supported_tasks":["synthetic_speech_detection"],"supported_sampling_parameters":[],"endpoints":{"synthetic_speech_detection":"/v1/audio/synthetic-speech"},"model_revision":"2026-10-05-adapt-216","is_ready":true,"availability":"paid_plans","is_free":true,"requires_paid_plan":true,"consumes_credits":false,"consumes_plan_minutes":false,"pricing_basis":"included_with_paid_plan","billing_note":"Included with every active paid plan. No credits, plan minutes or per-request fees are charged.","docs":"https://oruk.ai/docs/synthetic-speech"}]}