Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
JavaScript aianthropiccross-platformgeminigroqlinuxmacosnvidiaopen-sourceopenaiparakeetspeech-to-texttranscribewhisperwindows
feat(groq): add Qwen3.8 27B to the Groq model list (#2739)
Joel Tonya048e9f5f4bd
diff --git a/openwhispr-mobile/src/config/providerCatalog.json b/openwhispr-mobile/src/config/providerCatalog.jsonindex 8fd3dce7d..5491a2cae 100644--- a/openwhispr-mobile/src/config/providerCatalog.json+++ b/openwhispr-mobile/src/config/providerCatalog.json@@ -80,6 +80,10 @@"id": "openai/gpt-oss-120b","name": "GPT-OSS 120B"},+ {+ "id": "qwen/qwen3.8-27b",+ "name": "Qwen3.8 27B"+ },{"id": "openai/gpt-oss-20b","name": "GPT-OSS 20B"diff --git a/scripts/llm-canary.mjs b/scripts/llm-canary.mjsindex e43ff260a..ca9e33147 100644--- a/scripts/llm-canary.mjs+++ b/scripts/llm-canary.mjs@@ -49,7 +49,7 @@ const PROVIDERS = [id: "groq",keyEnv: "LLM_CANARY_GROQ_KEY",base: "https://api.groq.com/openai/v1",- models: ["openai/gpt-oss-120b", "openai/gpt-oss-20b"],+ models: ["openai/gpt-oss-120b", "openai/gpt-oss-20b", "qwen/qwen3.8-27b"],},{id: "tinfoil",diff --git a/src/locales/ar/translation.json b/src/locales/ar/translation.jsonindex c37d85097..5a55b5e4a 100644--- a/src/locales/ar/translation.json+++ b/src/locales/ar/translation.json@@ -295,6 +295,7 @@"gemini_gemma_4_31b_it": "أكبر نموذج Gemma 4 من Google، نموذج كثيف بحجم 31B، سياق 256K","gemini_gemma_4_26b_a4b_it": "نموذج Gemma 4 MoE من Google، بمعلمات نشطة 4B، سياق 256K","groq_openai_gpt_oss_120b": "نموذج OpenAI مفتوح المصدر الرائد، 500 رمز/ثانية",+ "groq_qwen_qwen3_8_27b": "نموذج Qwen سريع، 450 رمز/ثانية، سياق 131K","groq_openai_gpt_oss_20b": "نموذج سريع مفتوح المصدر، 1000 رمز/ثانية","groq_compound": "نظام Groq المركب، 450 رمز/ثانية","groq_compound_mini": "نظام مركب سريع، زمن انتقال أقل بمقدار 3 أضعاف",diff --git a/src/locales/de/translation.json b/src/locales/de/translation.jsonindex 96bb823c4..decf40ee3 100644--- a/src/locales/de/translation.json+++ b/src/locales/de/translation.json@@ -2784,6 +2784,7 @@"gemini_gemma_4_31b_it": "Googles größtes Gemma 4, 31B dicht, 256K Kontext","gemini_gemma_4_26b_a4b_it": "Googles Gemma 4 MoE, 4B aktive Parameter, 256K Kontext","groq_openai_gpt_oss_120b": "OpenAIs Open-Source-Flaggschiff, 500 T/s",+ "groq_qwen_qwen3_8_27b": "Schnelles Qwen-Modell, 450 T/s, 131K Kontext","groq_openai_gpt_oss_20b": "Schnelles Open-Source-Modell, 1000 T/s","groq_compound": "Groqs Compound-System, 450 T/s","groq_compound_mini": "Schnelles Compound-System, 3x niedrigere Latenz",diff --git a/src/locales/en/translation.json b/src/locales/en/translation.jsonindex 951f66534..d34aa46e4 100644--- a/src/locales/en/translation.json+++ b/src/locales/en/translation.json@@ -2784,6 +2784,7 @@"gemini_gemma_4_31b_it": "Google's largest Gemma 4, 31B dense, 256K context","gemini_gemma_4_26b_a4b_it": "Google's Gemma 4 MoE, 4B active params, 256K context","groq_openai_gpt_oss_120b": "OpenAI's open-source flagship, 500 T/sec",+ "groq_qwen_qwen3_8_27b": "Fast Qwen model, 450 T/sec, 131K context","groq_openai_gpt_oss_20b": "Fast open-source model, 1000 T/sec","groq_compound": "Groq's compound system, 450 T/sec","groq_compound_mini": "Fast compound system, 3x lower latency",diff --git a/src/locales/es/translation.json b/src/locales/es/translation.jsonindex 8d1d1c125..47ad22e87 100644--- a/src/locales/es/translation.json+++ b/src/locales/es/translation.json@@ -2738,6 +2738,7 @@"gemini_gemma_4_31b_it": "El mayor Gemma 4 de Google, 31B denso, contexto 256K","gemini_gemma_4_26b_a4b_it": "Gemma 4 MoE de Google, 4B parámetros activos, contexto 256K","groq_openai_gpt_oss_120b": "Modelo insignia de código abierto de OpenAI, 500 T/seg",+ "groq_qwen_qwen3_8_27b": "Modelo Qwen rápido, 450 T/seg, contexto de 131K","groq_openai_gpt_oss_20b": "Modelo de código abierto rápido, 1000 T/seg","groq_compound": "Sistema compound de Groq, 450 T/seg","groq_compound_mini": "Sistema compound rápido, 3x menor latencia",diff --git a/src/locales/fr/translation.json b/src/locales/fr/translation.jsonindex d5f302fac..6d25d37ca 100644--- a/src/locales/fr/translation.json+++ b/src/locales/fr/translation.json@@ -2784,6 +2784,7 @@"gemini_gemma_4_31b_it": "Le plus grand Gemma 4 de Google, 31B dense, contexte 256K","gemini_gemma_4_26b_a4b_it": "Gemma 4 MoE de Google, 4B paramètres actifs, contexte 256K","groq_openai_gpt_oss_120b": "Modèle phare open source d'OpenAI, 500 T/s",+ "groq_qwen_qwen3_8_27b": "Modèle Qwen rapide, 450 T/s, contexte 131K","groq_openai_gpt_oss_20b": "Modèle open source rapide, 1000 T/s","groq_compound": "Système compound de Groq, 450 T/s","groq_compound_mini": "Système compound rapide, 3x latence réduite",diff --git a/src/locales/it/translation.json b/src/locales/it/translation.jsonindex 63ce83044..0ca753fda 100644--- a/src/locales/it/translation.json+++ b/src/locales/it/translation.json@@ -2686,6 +2686,7 @@"gemini_gemma_4_31b_it": "Il più grande Gemma 4 di Google, 31B denso, contesto 256K","gemini_gemma_4_26b_a4b_it": "Gemma 4 MoE di Google, 4B parametri attivi, contesto 256K","groq_openai_gpt_oss_120b": "Ammiraglia open source di OpenAI, 500 T/sec",+ "groq_qwen_qwen3_8_27b": "Modello Qwen veloce, 450 T/sec, contesto 131K","groq_openai_gpt_oss_20b": "Modello open source veloce, 1000 T/sec","groq_compound": "Sistema compound di Groq, 450 T/sec","groq_compound_mini": "Sistema compound veloce, 3x latenza ridotta",diff --git a/src/locales/ja/translation.json b/src/locales/ja/translation.jsonindex 77799c52e..2238ba898 100644--- a/src/locales/ja/translation.json+++ b/src/locales/ja/translation.json@@ -2686,6 +2686,7 @@"gemini_gemma_4_31b_it": "Google 最大の Gemma 4、31B デンス、256K コンテキスト","gemini_gemma_4_26b_a4b_it": "Google の Gemma 4 MoE、4B アクティブパラメータ、256K コンテキスト","groq_openai_gpt_oss_120b": "OpenAI のオープンソースフラッグシップ、500 T/秒",+ "groq_qwen_qwen3_8_27b": "高速 Qwen モデル、450 T/秒、131K コンテキスト","groq_openai_gpt_oss_20b": "高速オープンソースモデル、1000 T/秒","groq_compound": "Groq の Compound システム、450 T/秒","groq_compound_mini": "高速 Compound システム、3x 低レイテンシー",diff --git a/src/locales/pt/translation.json b/src/locales/pt/translation.jsonindex 6cac76ade..bb58e7a55 100644--- a/src/locales/pt/translation.json+++ b/src/locales/pt/translation.json@@ -2665,6 +2665,7 @@"gemini_gemma_4_31b_it": "O maior Gemma 4 do Google, 31B denso, contexto 256K","gemini_gemma_4_26b_a4b_it": "Gemma 4 MoE do Google, 4B parâmetros ativos, contexto 256K","groq_openai_gpt_oss_120b": "Modelo principal open source da OpenAI, 500 T/seg",+ "groq_qwen_qwen3_8_27b": "Modelo Qwen rápido, 450 T/seg, contexto de 131K","groq_openai_gpt_oss_20b": "Modelo open source rápido, 1000 T/seg","groq_compound": "Sistema compound da Groq, 450 T/seg","groq_compound_mini": "Sistema compound rápido, 3x menor latência",diff --git a/src/locales/ru/translation.json b/src/locales/ru/translation.jsonindex b25c3a85b..3c8796e1a 100644--- a/src/locales/ru/translation.json+++ b/src/locales/ru/translation.json@@ -2702,6 +2702,7 @@"gemini_gemma_4_31b_it": "Крупнейшая Gemma 4 от Google, 31B плотная, контекст 256K","gemini_gemma_4_26b_a4b_it": "Gemma 4 MoE от Google, 4B активных параметров, контекст 256K","groq_openai_gpt_oss_120b": "Открытая флагманская модель OpenAI, 500 т/с",+ "groq_qwen_qwen3_8_27b": "Быстрая модель Qwen, 450 т/с, контекст 131K","groq_openai_gpt_oss_20b": "Быстрая открытая модель, 1000 т/с","groq_compound": "Система Compound от Groq, 450 т/с","groq_compound_mini": "Быстрая система Compound, 3x ниже задержка",diff --git a/src/locales/zh-CN/translation.json b/src/locales/zh-CN/translation.jsonindex f0ea269e6..c3e71985b 100644--- a/src/locales/zh-CN/translation.json+++ b/src/locales/zh-CN/translation.json@@ -2686,6 +2686,7 @@"gemini_gemma_4_31b_it": "Google 最大的 Gemma 4,31B 稠密,256K 上下文","gemini_gemma_4_26b_a4b_it": "Google Gemma 4 MoE,4B 活跃参数,256K 上下文","groq_openai_gpt_oss_120b": "OpenAI 开源旗舰,500 T/秒",+ "groq_qwen_qwen3_8_27b": "快速 Qwen 模型,450 T/秒,131K 上下文","groq_openai_gpt_oss_20b": "快速开源模型,1000 T/秒","groq_compound": "Groq Compound 系统,450 T/秒","groq_compound_mini": "快速 Compound 系统,3x 更低延迟",diff --git a/src/locales/zh-TW/translation.json b/src/locales/zh-TW/translation.jsonindex 42e58ed87..960ba9a93 100644--- a/src/locales/zh-TW/translation.json+++ b/src/locales/zh-TW/translation.json@@ -2686,6 +2686,7 @@"gemini_gemma_4_31b_it": "Google 最大的 Gemma 4,31B 稠密,256K 上下文","gemini_gemma_4_26b_a4b_it": "Google Gemma 4 MoE,4B 活躍參數,256K 上下文","groq_openai_gpt_oss_120b": "OpenAI 開源旗艦,500 T/sec",+ "groq_qwen_qwen3_8_27b": "快速 Qwen 模型,450 T/sec,131K 上下文","groq_openai_gpt_oss_20b": "快速開源模型,1000 T/sec","groq_compound": "Groq Compound 系統,450 T/sec","groq_compound_mini": "快速 Compound 系統,3x 更低延遲",diff --git a/src/models/modelRegistryData.json b/src/models/modelRegistryData.jsonindex 0afa897c4..213a024ce 100644--- a/src/models/modelRegistryData.json+++ b/src/models/modelRegistryData.json@@ -749,6 +749,13 @@"options": ["low", "medium", "high"]}},+ {+ "id": "qwen/qwen3.8-27b",+ "name": "Qwen3.8 27B",+ "description": "Fast Qwen model, 450 T/sec, 131K context",+ "disableThinking": true,+ "descriptionKey": "models.descriptions.cloud.groq_qwen_qwen3_8_27b"+ },{"id": "openai/gpt-oss-20b","name": "GPT-OSS 20B",diff --git a/src/services/ai/modelFamilyConstraints.ts b/src/services/ai/modelFamilyConstraints.tsindex 54ad4a68f..3010daad7 100644--- a/src/services/ai/modelFamilyConstraints.ts+++ b/src/services/ai/modelFamilyConstraints.ts@@ -48,8 +48,9 @@ const FAMILIES: Array<ModelFamilyConstraints & { match: RegExp }> = [{family: "qwen",match: /qwen/,- // qwen3 accepts none|default only (Groq's enum; "none" is also what the- // generic dialect sends everywhere, so the fact is provider-agnostic).+ // "none" turns Qwen's thinking off on Groq (which also takes+ // default|low|medium|high) and in the generic dialect, so the fact is+ // provider-agnostic.reasoningEffort: { suppressValue: "none", options: ["none"] },},{diff --git a/test/services/llmRequestShapeMatrix.test.js b/test/services/llmRequestShapeMatrix.test.jsindex 37f18de9a..3ecb2579d 100644--- a/test/services/llmRequestShapeMatrix.test.js+++ b/test/services/llmRequestShapeMatrix.test.js@@ -24,6 +24,8 @@ const MATRIX = [{ max_tokens: MAX_TOKENS, temperature: 0, reasoning_effort: "low" }],["groq gpt-oss suppression floors at low, never none (#990)", "Groq", "openai/gpt-oss-120b", null, CLEANUP_NO_THINK,{ max_tokens: MAX_TOKENS, temperature: 0, reasoning_effort: "low" }],+ ["groq qwen is registry-flagged disableThinking and always suppressed", "Groq", "qwen/qwen3.8-27b", null, CLEANUP,+ { max_tokens: MAX_TOKENS, temperature: 0, reasoning_effort: "none" }],["groq unknown family gets no guessed reasoning params", "Groq", "llama-3.3-70b-versatile", null, CLEANUP_NO_THINK,{ max_tokens: MAX_TOKENS, temperature: 0 }],