I want to share a Siri / Apple Intelligence issue I have been troubleshooting since the iOS 27 beta cycle, together with the configuration that finally resolved it. The issue started during iOS 27 beta, continued across multiple beta builds, and was still present after I updated to the official iOS 27 release. Updating iOS alone never fixed it. The main problem was that Siri / Apple Intelligence repeatedly failed to complete activation. Settings would remain stuck on: “Adding support for Siri is in progress” The Siri app would sometimes show: “Siri is not available” Siri also frequently fell back to the older floating-sphere interface instead of using the newer glowing-edge interface. Sometimes the new Siri interface would suddenly appear and work normally, but later it would fall back again. The most repeatable symptom involved charging. When the iPhone was connected to power, Siri sometimes appeared to finish downloading and would temporarily work normally. After disconnecting the charger, Siri could become unavailable again or the system would behave as though Siri resources still needed to be downloaded. Connected to power → Siri sometimes worked normally Disconnected from power → Siri could return to downloading / unavailable There was also a difference between Wi-Fi and cellular data. On cellular data, iOS sometimes said Wi-Fi was required to continue downloading Siri resources. After connecting to Wi-Fi, it would return to “Adding support for Siri is in progress” and still fail to finish. Apple Intelligence storage also behaved abnormally. At one point, iPhone Storage showed approximately 7.37 GB in use. Later, the Apple Intelligence entry disappeared and storage usage decreased, then reappeared after changing language settings. Before finding the working configuration, I had already tried restarting, Reset All Settings, Recovery Mode update, multiple iOS 27 beta builds, the official iOS 27 release, different Wi-Fi networks, cellular data, disabling VPN/proxy, changing languages, removing additional languages, switching between old and new Siri, and leaving the phone on Wi-Fi and power for long periods. None provided a permanent fix. After repeated testing, the issue appeared to involve network transport, routing consistency, Siri language / voice configuration, Siri AI authorization, and local asset refresh. My final working setup was: System language: English (United States) Region: United States Siri language: English (United States) Siri voice: American Apple Intelligence enabled Proxy environment: Shadowrocket Proxy transport My proxy node uses an AnyTLS-based configuration. Previously, UDP traffic was enabled. During troubleshooting, some Apple / iCloud requests appeared unreliable when using UDP / QUIC through this node, with timeouts, resets, or repeated retries. I changed the node transport to TCP only while keeping TLS enabled: TCP + TLS After this change, Apple-related authentication and asset requests appeared much more stable. Routing rules This was one of the most important changes. I use split tunneling so that Chinese apps can remain DIRECT while selected traffic uses the proxy. However, some Apple traffic was being matched by broader fallback rules such as: apple.com,DIRECT GEOIP,CN,DIRECT This meant some Siri / iCloud / Apple Intelligence requests could use the proxy while related requests went directly through the local connection. I added these high-priority rules and moved them above broader Apple / DIRECT / GEOIP rules: DOMAIN-KEYWORD,gateway,PROXY DOMAIN-KEYWORD,probe,PROXY DOMAIN-KEYWORD,gdmf,PROXY DOMAIN-KEYWORD,guzzoni,PROXY DOMAIN-SUFFIX,iphone-ld.apple.com,PROXY Rule priority was important. If broader DIRECT rules were above these entries, the specific traffic could still bypass the proxy. After moving these rules to the top, the relevant Apple traffic consistently followed the same network path. Split tunneling still worked normally, and apps such as WeChat, Alipay, Meituan, and Xiaohongshu could remain DIRECT. Language and Siri configuration I standardized the Siri environment: System Language: English (United States) Region: United States Siri Language: English (United States) Siri Voice: American I selected an American Siri voice, such as Voice 4. After changing everything to the same English (US) environment, asset loading became more consistent. Enable Siri AI I manually selected: Try Siri AI (Beta) and completed the authorization process. I also temporarily disabled “Require Face ID” for the standalone Siri app while troubleshooting. I cannot confirm that this directly affected the download, but it removed an extra authentication layer while testing. Refresh local language assets I opened Apple’s built-in Translate app, deleted the downloaded English (US) language package, and downloaded it again. My goal was to refresh the local language / MobileAsset download state. I cannot confirm that Translate directly controls Siri’s generative models, but this appeared to help clear the remaining stuck asset state. Final installation step After making all of the above changes, I connected the iPhone to Wi-Fi and power, locked the screen, and left the device idle for approximately 10–15 minutes. After this, the Siri / Apple Intelligence state finally changed and remained stable. Current result: Siri consistently uses the full-screen glowing-edge interface Type to Siri works correctly Siri no longer falls back to the legacy floating-sphere interface “Siri is not available” no longer appears “Adding support for Siri is in progress” is no longer permanently stuck Apple Intelligence remains active Siri continues working after disconnecting the charger Split tunneling still works normally Most importantly, the previous charging-related behavior is gone. Before: Connected to power → Siri temporarily worked Disconnected from power → Siri failed again Now: Siri continues to work normally whether or not the device is connected to power. I am not claiming that Apple has officially documented every domain or internal process above as the root cause. These findings are based on repeated troubleshooting and network behavior observed on my own device. However, this issue persisted from the iOS 27 beta cycle through the official iOS 27 release, and standard system updates alone did not resolve it. In my case, the successful fix only came after correcting the combination of: TCP transport + consistent Apple routing + English (US) system / Siri configuration + Siri AI authorization + local asset refresh. If anyone else is experiencing “Adding support for Siri is in progress,” “Siri is not available,” repeated fallback to the legacy Siri UI, Apple Intelligence storage disappearing / reappearing, or Siri working while charging but failing after unplugging, I would be interested to know whether the same configuration also resolves the issue on other devices.

Hi everyone, I've submitted a Feedback request (FB23469644) asking to introduce a generic Transportation Journey schema for App Intents. At the moment, there doesn't seem to be a way to donate structured public transportation trips (train, flight, bus, ferry, etc.) to Siri's semantic index. While many travel apps already have rich journey data, there is no common semantic model that represents: Multi-leg journeys Departure and arrival stations/airports/stops Platforms, tracks, gates, terminals Scheduled and real-time departure/arrival information Delays and cancellations Ticket and reservation information This seems like a natural addition to the existing App Intents schemas and would enable Siri, Spotlight, and Apple Intelligence to better understand upcoming journeys across all transportation providers. If you're building a travel or mobility app and have encountered the same limitation, I'd appreciate hearing your thoughts. Any idea if the old Siri event suggestion API gets is indexed by Siri Semantic Index / Siri AI?

Estou compartilhando algumas observações técnicas sobre Crash Detection / Emergency SOS no ecossistema Apple, com base em eventos amplamente observados em 2022 e 2024, quando houve chamadas automáticas em massa para serviços de emergência. A ideia aqui não é discutir UX superficial ou “edge cases isolados”, mas sim comportamento sistêmico em escala, algo que acredito ser relevante para qualquer time que trabalhe com sistemas críticos orientados a eventos físicos. Contexto resumido A partir do iPhone 14, a Detecção de Acidente passou a correlacionar múltiplos sensores (acelerômetros de alta faixa, giroscópio, GPS, microfones) para inferir eventos de impacto severo e acionar automaticamente chamadas de emergência. Em 2022, isso resultou em um volume significativo de falsos positivos, especialmente em atividades com alta aceleração (esqui, snowboard, parques de diversão). Em 2024, apesar de ajustes, houve recorrência localizada do mesmo padrão. Ponto técnico central O problema não parece ser hardware, nem um “bug pontual”, mas sim o estado intermediário de decisão: Aceleração ≠ acidente Ruído ≠ impacto real Movimento extremo ≠ incapacidade humana Quando o classificador entra em estado ambíguo, o sistema depende de uma janela curta de confirmação humana (toque/voz). Em ambientes ruidosos, com o usuário em movimento ou fisicamente ativo, essa confirmação frequentemente falha. O sistema então assume incapacidade e executa a ação fail-safe: chamada automática. Do ponto de vista de engenharia de segurança, isso é compreensível. Do ponto de vista de escala, é explosivo. Papel da Siri A Siri não “decide” o acidente, mas é um elo sensível na cadeia humano–máquina. Falhas de compreensão por ruído, idioma, respiração ofegante ou ausência de resposta acabam sendo interpretadas como sinal de emergência real. Isso é funcionalmente equivalente ao que vemos em sistemas automotivos como o eCall europeu, quando a confirmação humana é inexistente ou degradada. O dilema estrutural Há um trade-off claro e inevitável: Reduzir falsos negativos (não perder um acidente real) Aumentar falsos positivos (chamadas indevidas) Para o usuário individual, errar “para mais” faz sentido. Para serviços públicos de emergência, milhões de dispositivos errando “para mais” criam ruído operacional real. Por que isso importa para developers A Apple hoje opera, na prática, um dos maiores sistemas privados de segurança pessoal automatizada do mundo, interagindo diretamente com infraestrutura pública crítica. Isso coloca Crash Detection / SOS na mesma categoria de sistemas safety-critical, onde: UX é parte da segurança Algoritmos precisam ser auditáveis “Human-in-the-loop” não pode ser apenas nominal Reflexões abertas Alguns pontos que, como developer, acho que merecem discussão: Janelas de confirmação humana adaptativas ao contexto (atividade física, ruído). Cancelamento visual mais agressivo em cenários de alto movimento. Perfis de sensibilidade por tipo de atividade, claramente comunicados. Critérios adicionais antes da chamada automática quando o risco de falso positivo é estatisticamente alto. Não é um problema simples, nem exclusivo da Apple. É um problema de software crítico em contato direto com o mundo físico, operando em escala planetária. Justamente por isso, acho que vale uma discussão técnica aberta, sem ruído emocional. Curioso para ouvir perspectivas de quem trabalha com sistemas similares (automotivo, wearables, safety-critical, ML embarcado). — Rafa

Hey dear developers! This post should be available for the future Siri updates and improvements but also for wishes in this forum so that everyone can share their opinion and idea please stay friendly. have fun! I had already thought about developing a demo app to demonstrate my idea for a better Siri. My change of many: Wish Update: Siri's language recognition capabilities have been significantly enhanced. Instead of manually setting the language, Siri can now automatically recognize the language you intend to use, making language switching much more efficient. Simply speak the language you want to communicate in, and Siri will automatically recognize it and respond accordingly. Whether you speak English, German, or Japanese, Siri will respond in the language you choose.

Hello, I’m experiencing an issue with Siri on iOS where it prioritizes a contact from the wrong account, even though I’ve set a default account for Contacts. Details of the issue: I have two contact groups: Exchange (Outlook) — my default account. iCloud. There’s a contact, "Alena Jorse," which exists in both groups: In the Exchange group, the name is saved as Alena Jorse. In the iCloud group, it is saved as Alena Jorse with double-strike formatting (e.g., "Alena Jorse**"). Both contacts have the same phone number. When I ask Siri to call "Alena Jorse," it selects the iCloud contact ("Alena Jorse**") instead of the Exchange contact, despite Exchange being set as the default Contacts account in my iOS settings. Expected Behavior: Siri should prioritize the contact from the default account (Exchange) and ignore other accounts unless specified. Steps to Reproduce: Have duplicate contacts in two groups (Exchange and iCloud) with the same phone number. Set Exchange as the default Contacts account. Ask Siri to call the contact. Troubleshooting Steps Taken: Ensured the default account is set to Exchange. Verified both contacts have the same phone number. Tested by disabling iCloud temporarily, which resolves the issue (but is not a viable long-term solution). Request: Could you please advise if this is intended behavior or a bug? If it’s a configuration issue, how can I ensure Siri prioritizes the default account for contacts? If it’s a bug, could this be investigated further? Thank you for your assistance.

My requirement is to open a specific screen of my app with when user says " Start Sleep meditation for 10 minutes" where Sleep and 10 minutes are dynamic values in the phrase. Is it possible just with a phrase we can get the values. Or do i need to ask using siri "which meditation" and then "how much tine". I am planning to use AppIntent and AppShortcut, along with Entities. But unable to open the shortcut when siri invokes with phrase i discussed above.

It would be good if we could tallk to Siri with emojis as well. I’m pretty sure emojis are her’s native language.

'init(coordinateRegion:interactionModes:showsUserLocation:userTrackingMode:)' was deprecated in iOS 17.0: Use Map initializers that take a MapContentBuilder instead. struct EmMapView: View { @State private var region = MKCoordinateRegion( center: CLLocationCoordinate2D(latitude: 37.7749, longitude: -122.4194), span: MKCoordinateSpan(latitudeDelta: 0.1, longitudeDelta: 0.1) ) var body: some View { ZStack { Map(coordinateRegion: .constant(region), interactionModes: .all, showsUserLocation: false, userTrackingMode: .none) .edgesIgnoringSafeArea(.all) .navigationTitle("Emmap") } } }

Suddenly Siri can not find NPO Radio 5 in my HomePod Mini's. That is very strange because it has worked for month. The NPO Radio 5 is located in TuneIn and available as App on iPad/iPhone. This is a very personal problem for me, but the question is of course have other users find working Siri phrases that suddenly do not work?

Hi I think Siri is being developed. I think it is very wrong to display every action as a notification (like a photo) as a suggestion. I think it would be better to fix this and show it in the shortcuts area. Beta ios 16.2 has arrived and ios 16.3 is still in progress. best regards

for those of you who have clients who are concerned with privacy, note that you have to go into system prefs in your mac and dig into the "siri suggestions and privacy" and shut off sirl for all the apps listed there, if in fact you don't want siri scanning your data. it is not enough to shut off "enable ask siri" at the top level. i found this out when siri scanned open safari pages and wanted to add things to my calendar. what? apple must have hired some google employees, heh.

I develop my an IM app for support Siri suggestion feature. I donate a INSendMessageIntent when user send message in group. I create INPerson array by users in that group. But the photo share sheet only show max 20 persons, the trust is I set persons parameters count is 56. Who can explain why limit show max group users count, or my anything wrong? I circle the key point in picture by red pencil. The second and the fourth chat that users in group count more than 20.

I was trying to access a website that ends with .wiki. The URL was registered to the DNS server. However, instead of going to the actual website, Siri suggestion took me to a Wikipedia page that was totally irrelevant. Since Siri suggestion came at the top, everyone who tried to access the website almost cannot get it right for the first time. This contamination occurs after upgrading to Monterey. Is there anyway to let the devs know the situation?

I’d like to see if someone is in my account

I have got disabled Siri suggestions (general & individual for apps), but everytime on locked screen it appears notoriously (for almost anything: safari, photos, ...). Never got that kind of problems in iOS12. Do you have any working solutions? I've been fighting with that problem for over a year now - it's so frustrating.

Hello, I am not able to use or \n to take a new line in the email body in the default iOS mail application. Example: mailto:abc@gmailDOTcom?subject=test&body=Hello,mailBody Result in latest iOS mail app: Hello,mailBody Expected result: Hello, mailBody Will you please help me to resolve this issue?

I would like to have access to Siri Voice in AVSpeechSynthesizer to read text in our applications. I checked that it can already be accessed in Voice Over but not in Speech. I don't know if it can already be done in iOS 15. I need your help. Please.