On-Device AI: Asistente

On-Device AI reúne chat, esc

Acerca de esta app

On-Device AI reúne chat, escucha, transcripción, notas e investigación en una sola app privada para iPhone, iPad, Mac y Apple Vision Pro. Tus datos se quedan en tu dispositivo.
Descarga un modelo una vez y la app sigue funcionando en un avión, en el metro o sin cobertura. Chats, documentos, grabaciones y notas se procesan en tu dispositivo. Los proveedores y las funciones web solo se usan cuando los activas.
UNA APP, A TU MANERA 
Abre todos los espacios de trabajo desde un Menú personalizable: favoritos en Fijados y el resto en Disponibles.
CHAT IA 
Conversa con modelos locales o en la nube. 
• Explorar, descargar y gestionar modelos de Gemma, Qwen, DeepSeek y Mistral, o conectar tu propia cuenta de proveedor 
• Añadir documentos, imágenes y PDF escaneados; autorizar OCR privado en el dispositivo solo cuando un PDF lo necesite 
• Dejar que el modelo use herramientas para cálculos, peticiones web, documentos, Calendario y Recordatorios, y revisar los cambios propuestos antes de aplicarlos 
• Crear Agent Profiles reutilizables y añadir las AI Skills, los servidores MCP y las herramientas adecuadas desde Flujos de agentes 
• Bifurcar conversaciones, comparar modelos y guardar datos frecuentes en Memoria global
BIBLIOTECA DE ESCUCHA Y FUENTES RSS 
Leer menos, escuchar más. 
• Convertir PDF, Markdown, texto sin formato, artículos web y libros escaneados en una cola de escucha 
• Escanear páginas fotografiadas, corregir el OCR local de la app y conservar cada página con su texto leído 
• Seguir sitios por fuentes RSS, Atom y JSON, y enviar artículos a A continuación 
• Elegir voces de Apple o voces neuronales locales, seguir el texto en el lector y poner un temporizador de reposo
NOTA DE VOZ, ESCRITURA POR VOZ Y TEXTO A VOZ 
Hablar en vez de escribir y escuchar en vez de leer. 
• Grabar y transcribir reuniones, clases, entrevistas e ideas rápidas 
• Dictar con Escritura por voz en el Mac o con el teclado de voz en iPhone y iPad 
• Transcribir con Apple Speech, Whisper, Parakeet, Nemotron, Qwen3-ASR, MOSS y otros motores 
• Convertir en audio un texto, o el texto de una foto, con voces de Apple, Kokoro, Supertonic, VoxCPM2, IndexTTS2 y otros motores 
• Exportar transcripciones como texto, subtítulos o Markdown
BÚSQUEDA IA Y NAVEGADOR IA 
Investigar con una ayuda extra. 
• Buscar en la web dentro de una conversación y dejar que el modelo lea los resultados 
• Navegar con pestañas, perfiles, historial y descargas, pedir al modelo que lea, ayude o actúe, y retomar una tarea del navegador cuando quieras
CONOCIMIENTO Y NOTA DE TEXTO 
Dar a tu IA tu propio material para trabajar. 
• Añadir PDF, texto, Markdown, código, imágenes y contenido de sitios web a una biblioteca privada y consultable 
• Escribir notas en Markdown, importar chats de IA, notas de voz, elementos de Texto a voz y resultados de Búsqueda IA, y volver a indexar el contenido editado
AYUDA DE LA APP 
Pregunta por una función o un ajuste. Ayuda de la app responde desde una guía integrada, no guarda esas consultas en tus chats y te lleva al ajuste adecuado.
HECHO PARA DISPOSITIVOS APPLE 
• Navegación y ajustes adaptados, del iPhone a la barra lateral 
• Ajustes por función: Escritura por voz, Flujos de agentes, Modelos y almacenamiento, Privacidad y datos, Memoria global y Mensajería en el Mac 
• Aceleración por hardware de Apple para modelos locales compatibles 
• Explorar modelos de chat, transcripción, voz y embeddings en una sola Biblioteca de modelos 
• Guardar los modelos en el almacenamiento interno, un disco externo o un volumen compartido, con herramientas separadas para limpieza y recuperación 
• En el Mac, conectar apps de mensajería para que el modelo redacte o envíe respuestas según tus reglas 
• Interfaz en alemán, chino tradicional, español, francés, inglés, italiano, japonés, neerlandés y portugués
EULA: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Aspectos destacados

Runs local LLMs (Gemma, Qwen, DeepSeek) for offline chat and reasoning

Converts PDFs, articles, and voice notes to audio using local neural voices

Integrates AI browser agents and web search within private conversations

Supports custom Agent Workflows with MCP servers and external tools

Actualizaciones de versión

Versión 1.51.0

What's new in 1.51.0 • Keep track of replies across chats with activity shown in history and Continue for saved partial answers. Starting another local reply pauses the earlier one and saves its progress; cloud chats can run alongside each other within your device's limits. Regenerating an answer keeps the original until its replacement is saved successfully. Stop controls now stay available when switching cloud chats, and Thinking is kept separate from the answer. • Models are easier to remove from the model picker. You can also follow download progress and cancel a download, with speed and estimated time remaining shown when enough data is available. Download status is more reliable after reopening the app. • The model picker has fewer repeated status labels. On iPhone, the Last Used card stays out of the way while you browse and returns when you scroll back to the top, without flickering in and out. • Hugging Face GGUF file links now point to the download. Repository links direct you to the model browser, and small model sizes display correctly. The model library's navigation title is visible again on iPhone. • Free up storage after removing models without restarting the app. Model Storage updates which shared files are still needed and explains which installed models depend on them. • Chat input on iPhone and iPad keeps your draft and attachments when you expand or close it. Keyboard focus and transitions are smoother, including when you tap quickly or open the side menu. These changes help you return to unfinished chats and free up storage with fewer steps, so you can spend more time on the conversation.

5/10/2026 · Apple App Store · iOS · Ver fuente

Versión 1.50.0

Version 1.50.0 makes AI Chat more dependable while you move between conversations, and gives you more ways to transcribe on iPhone and iPad. • Start a reply, open another conversation, and return to find the response where it belongs. If a response is interrupted, you can retry from that conversation, with any saved partial output retained. • Local chat models now show which engine they use in the model picker, making similar versions easier to tell apart. We also updated the engine behind local chat for faster responses. • More transcription models are available on supported iPhone and iPad devices, including additional Parakeet, Canary, Nemotron, Cohere, and MOSS choices. Availability still depends on the device and model requirements. • Qwen3-ASR now offers four size and precision choices on eligible devices. You can remove an older download separately and choose a current one. Your recordings and transcripts stay where they are. • Voice Note on iPhone puts Record within easy reach and groups optional recording settings. Model details and download activity are clearer. Speech downloads show a Cancel button, and finished models are easier to find before you choose to use them. • Long transcription and speech jobs now use smaller chunks on supported local models to help keep memory use under control. The app still checks each model's limits. • Fixed Parakeet TDT v3 being marked incomplete after a successful download. On Mac, Canary 1B v2 now prepares without blocking the app and shows progress during audio imports.

30/9/2026 · Apple App Store · iOS · Ver fuente

Versión 1.49.0

Version 1.49.0 is for the work that starts with a long recording, a scanned document, or an idea you want to hear out loud. It also makes a growing app much easier to find your way around. • Recording a meeting, class, interview, or research session? MOSS Transcribe + Diarize is our recommended model for meeting notes. It separates speakers and now uses less memory, so long recordings can finish more reliably. Your original audio stays untouched. • Add a scanned report, paper, receipt, contract, or class handout to AI Chat and ask questions about it. If a PDF has no readable text, the app asks before running OCR on your device. You can follow progress page by page or cancel without leaving a half-finished attachment. • Supertonic, VoxCPM2 Int8, VoxCPM2 BF16, and IndexTTS2 are new in this release. Depending on the model and your device, you can make narration for a presentation, create a voiceover, listen back to your own writing, or use a saved reference voice. • The Menu now keeps the workspaces you use most under Pinned, with everything else under Available. Settings are grouped by purpose and adapt to the screen, whether you are on an iPhone or working with a sidebar on a larger device. • Agent Workflows are easier to set up. Start with an Agent Profile for a repeatable job, such as research or editing, then add the AI Skills, MCP servers, and tools it needs. On Mac, messaging app connections now have their own Settings area. • The Model Library is now the main place to browse, download, choose, repair, or remove chat, transcription, speech, and embedding models. Speech downloads also show clearer progress, including quiet stretches during large transfers. • Saved chats open correctly on the first try. Long answers scroll more smoothly, and you can begin reading before rich formatting is done. • Cloud requests have more time to respond. If one fails, the app stops cleanly, keeps any partial reply, and leaves a successfully loaded model ready for another try. • We also cleaned up the AI Chat model header and Voice Note controls. Conversation Mode returns to listening after it speaks, and deleting an active chat no longer lets old work bring it back.

15/9/2026 · Apple App Store · iOS · Ver fuente

Puntuación AppRank

El promedio de las valoraciones verificadas disponibles en las plataformas de esta app.

★ 4.4162 valoraciones

Promedio entre plataformas