# Amora developer documentation PUBLIC TECHNICAL PREVIEW. Production credentials, endpoints, allowances and contracts are agreed during onboarding. Examples marked illustrative are not live endpoint guarantees. # Introduction Source: https://amora.cam/docs Amora is infrastructure for branded AI companion businesses: conversational experiences, expressive voice, character identity, memory, content workflows and marketplace integration. Build a complete white-label platform or add selected capabilities to a product you already operate. > This documentation is a public technical preview. The live voice demonstration is available on the website. Production partner endpoints, credentials, usage allowances and integration terms are issued during onboarding. Illustrative examples here do not establish a currently available Amora API contract. ## Choose your starting point - **Try a character:** [Open the Amora voice demo](/market/amora/call) or listen to the preview on the [homepage](/). - **Integrate an existing product:** Start with the [quickstart](/docs/quickstart), then review [voice calls](/docs/voice-calls), [messaging](/docs/messaging) and [memory](/docs/memory). - **Launch your own platform:** Read the [white-label deployment guide](/docs/white-label). - **Create an identity:** Explore [Custom Character LoRA](/docs/custom-lora) and the [character examples](/#characters). - **Bring it to mobile:** Add a [branded mobile web experience and Telegram Mini App](/docs/mobile). ## What the stack includes | Layer | Purpose | | ----------------------- | ----------------------------------------------------------------- | | Conversational runtime | Character-aware text and real-time voice experiences | | Character system | Personality, behavior, expressive voice and visual identity | | Memory and knowledge | Profile continuity, summaries and retrieval context | | Content workflows | Character photos, generated clips and voice messages | | Marketplace integration | Subscriptions, paid content, creator onboarding and commerce | | Operations | Configuration, deployment, hosting and ongoing technical services | ## Work with our team We offer white-label deployments, API integration projects and regional partnerships. Configuration, installation, DevOps, consulting and LoRA training can also be ordered individually. [Contact amora@amora.cam](mailto:amora@amora.cam?subject=Amora%20integration) to arrange a technical walkthrough and agree the scope of your first release. ## Documentation for AI assistants The [documentation index](/llms.txt) lists every guide. The [complete text edition](/llms-full.txt) combines the documentation into one file. Both carry the same technical-preview status as this website. --- # Quickstart Source: https://amora.cam/docs/quickstart Start with the experience you want to create. We agree the character, channels, commercial model and integration scope before production activation. ## Step 1 — Experience the voice Listen to Amora on the [homepage](/) and start a test call. Calls require microphone permission; the recorded preview does not. The same demonstration remains available at [/market/amora/call](/market/amora/call). ## Step 2 — Choose an integration model | Model | Best starting point | | -------------------- | -------------------------------------------------------------- | | White-label platform | A new branded companion marketplace | | API and integration | An existing product with an audience | | Regional partnership | An operator leading traffic, distribution and local operations | Include your target audience, expected channels, launch scope and existing stack when contacting our team. ## Step 3 — Configure a character Agree a personality, conversational behavior, voice, knowledge context and memory policy. Add [Custom Character LoRA](/docs/custom-lora) when a consistent visual identity is part of the experience. The following is a product configuration sketch, not an API request: ```ts const experience = { brand: "Your brand", character: "Your character", channels: ["web", "mobile-web", "telegram"], voice: "expressive", memory: "configured during onboarding", }; ``` ## Step 4 — Receive integration details Our team provides the approved base URLs, environment-specific credentials, character identifiers and request contracts for your enabled services. Keep production keys on your server and exchange signed connection data with browsers. ## Step 5 — Test and launch Test conversation quality, microphone permissions, interruptions, disconnects, memory boundaries, content workflows and your payment model. Review [installation and operations](/docs/operations) before launching the pilot. **Next step:** [Request a technical walkthrough](mailto:amora@amora.cam?subject=Amora%20technical%20walkthrough). --- # Authentication Source: https://amora.cam/docs/authentication Production service credentials belong on your backend. Your browser, mobile web app or Telegram Mini App should receive only the scoped data needed for the current interaction. ## Production access Access is enabled by arrangement. We provide the service base URLs, authentication scheme, key scope and enabled capabilities during onboarding. A sales request does not automatically issue an API key. ## Keep keys on the server Store secrets in your deployment's runtime environment or secret store. Use separate credentials for development and production. Never place production credentials in browser bundles, public configuration, analytics events or documentation. ```bash # Illustrative server configuration; values are issued during onboarding. AMORA_API_BASE_URL=YOUR_ASSIGNED_BASE_URL AMORA_API_KEY=YOUR_SERVER_SIDE_KEY ``` Environment names above describe an integration convention. They are not evidence of a provisioned endpoint. ## Voice session credentials For a production voice integration, the backend creates the call. The client receives signed, call-specific connection data and uses the audio client to connect. The account-level key stays on the server. Signed links authorize a specific interaction. Treat them as credentials: do not log their query strings or put them in public links. ## Authentication differences The final service contract determines the required header. Some generation interfaces use a Bearer token; call-creation services may use an API-key header. Do not assume a single header works across every service until your integration contract confirms it. ## Rotation and access changes Arrange key rotation with our team, update the server configuration, verify the replacement and revoke the old key. Scope character access, usage and administrative operations to the needs of the integration. --- # Availability & access Source: https://amora.cam/docs/availability Use the status of a capability to distinguish a working demonstration, a configured project service and a proposed public API integration. ## Current capability status | Capability | Availability | | -------------------------------- | --------------------------------------------------------------- | | Real-time AI voice calls | Try the demo on this website | | AI content generation | Custom service; provider routes agreed for each project | | Persistent memory | Configured for your project | | AI-driven commerce | Custom integration | | White label and API | Sales-led projects; public documentation is a technical preview | | Mobile web and Telegram Mini App | Additional deployment feature | | AI video streaming | Coming soon | ## What a preview means The guides describe the intended integration architecture and important service behaviors. They do not promise public self-service endpoints, automatic key issuance, a particular model catalog or a fixed rate limit. A request example marked illustrative must be checked against the production contract issued to your project before use. ## Generated video and live streaming Generated clips are asynchronous content assets. Real-time video streaming is a different capability and is currently in development. Availability of a clip-generation provider does not make live video avatars available. ## Request access Send your project scope and preferred plan to [amora@amora.cam](mailto:amora@amora.cam?subject=Amora%20API%20access). We confirm the enabled services, commercial allowance, environments and launch requirements before activation. --- # Messaging Source: https://amora.cam/docs/messaging Build conversations around a defined character, the user's recent messages and the context your product is allowed to retain. ## Conversation flow 1. Authenticate the user in your product. 2. Load the permitted character configuration and relevant conversation context. 3. Submit the message from your backend. 4. Stream or return the response to the user. 5. Store the resulting conversation according to your project's memory and retention settings. ## Illustrative request The following shows an OpenAI-compatible generation pattern for a proposed integration. Your assigned production endpoint and model identifier are confirmed during onboarding. ```bash curl "$AMORA_API_BASE_URL/v3/chat/completions" \ -H "Authorization: Bearer $AMORA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "YOUR_ASSIGNED_MODEL", "messages": [ {"role": "system", "content": "Use the approved character configuration."}, {"role": "user", "content": "How has your day been?"} ], "stream": true }' ``` This example is illustrative and is not a currently executable Amora endpoint guarantee. ## Character and knowledge context Keep the character's identity and behavior in configuration owned by your project. Add selected [knowledge](/docs/knowledge) and [memory](/docs/memory) context on the server. Maintain clear boundaries between different users, characters and customer workspaces. ## Streaming responses Plan for connection interruption, partial responses and user cancellation. Preserve the response accumulated so far and distinguish incomplete output from a fully completed message. Do not automatically repeat a paid generation when its outcome is unknown. ## Usage Token accounting, model availability and any fallback behavior are part of your enabled service configuration. Agree those limits before publishing an allowance to your customers. --- # Real-time voice calls Source: https://amora.cam/docs/voice-calls The voice experience combines a configured character, real-time audio transport and the lifecycle controls in your application. ## Try the demonstration Use **Call Amora** on the [homepage](/) to open the in-page call panel. You can also use the existing [character call page](/market/amora/call). Microphone permission is requested when you start a call; you can mute or hang up from the panel. ## Server-initiated architecture ```text User chooses Call → Browser obtains microphone permission → Your backend creates a character call → Backend returns scoped connection data → Audio client establishes the real-time connection → Your application tracks connection and completion ``` The account-level API key remains on your server. Browsers receive signed session data rather than that key. ## Illustrative creation contract A call-creation integration can use a fixed configured character and a server-enforced duration limit. This request is a preview of the integration pattern; use your assigned production contract before deployment. ```json { "character": "YOUR_ASSIGNED_CHARACTER", "call_time_limit_seconds": "300" } ``` The integration returns call-specific connection data. While a call is starting, the application checks readiness before opening the audio connection. Preserve signed URLs and query parameters exactly as issued. ## Call states | State | Application behavior | | ---------- | ---------------------------------------------------------- | | Idle | Show the call action and recorded preview | | Connecting | Prevent duplicate starts; allow cancellation | | Connected | Show elapsed time, voice activity, mute and hang-up | | Ended | Release microphone and audio resources; offer another call | | Error | Show a clear message and an explicit retry action | ## Microphone and cleanup Acquire audio only after the user's call action. Keep ownership of the microphone stream so cancellation can stop it even if initialization is incomplete. Stop late-resolving streams after cancellation. On close, hang-up or page exit, stop local tracks, close the audio client and request server-side call termination. Stop the voice preview before opening a live call. ## Mobile behavior Use HTTPS, clear permission guidance, touch-sized controls and safe-area spacing. Handle permission denial, unavailable devices, network changes and interruptions. Review the [mobile guide](/docs/mobile) for the channel-specific considerations. --- # Speech & transcription Source: https://amora.cam/docs/speech Use speech generation for character voice messages and audio content. Use transcription to turn recorded user audio into text for your conversation workflow. ## Speech generation A typical speech job receives text and an assigned voice, then returns an audio result. The voice, language, output format and supported controls depend on your configured service. The following is an illustrative request body for the integration preview: ```json { "model": "YOUR_ASSIGNED_SPEECH_MODEL", "voice": "YOUR_CHARACTER_VOICE", "input": "I was hoping you would call." } ``` The assigned production contract determines the endpoint and whether the response is audio bytes or a job/result reference. ## Recorded previews Provide a short, representative sample before asking a visitor to start a live call. Playback should begin after a user action, show a play/pause state and stop when a live session begins. Amora's homepage uses the same recording as the character demonstration, with an audio-format fallback for compatibility. ## Transcription A transcription workflow accepts an audio file or an approved file URL, submits it for processing and retrieves the result. For asynchronous jobs, retain the job identifier and check status rather than submitting the same recording repeatedly. Language selection, supported file formats, payload limits and transcript retention are confirmed in your production service configuration. ## Content delivery Deliver voice messages through your asset storage and access-control layer. Paid messages should be available only to users with the required entitlement. Decide whether to retain source text and audio as part of the [content workflow](/docs/content-generation). --- # Voice management Source: https://amora.cam/docs/voice-management A character's voice is part of its identity. Configure the voice and conversational behavior together so the experience feels consistent across channels. ## Configuration service We can configure an expressive voice, tune character presentation and validate the result against your intended audience. Include language, conversational style, reference examples and channel requirements in the brief. ## Creator-based voices For a creator-based character, agree the rights, approved uses, sample requirements and intended distribution with the creator. The training and voice configuration approach is scoped separately from a generic character setup. Sample duration and quality requirements vary with the selected voice workflow; we confirm those requirements before collection. ## Processing workflow 1. Agree the target character and voice brief. 2. Prepare and review the required recordings. 3. Submit the configured processing workflow. 4. Check readiness and review representative samples. 5. Assign the approved voice to the character. 6. Validate live calls and recorded voice messages. ## Operational changes Version voice changes and keep a reference sample for comparison. Test new configurations before changing a voice used by existing customers. Coordinate any rollback with the character configuration and speech model settings. [Request voice configuration](mailto:amora@amora.cam?subject=Character%20and%20voice%20configuration). --- # Persistent memory Source: https://amora.cam/docs/memory Persistent memory is the application layer that gives a character continuity across sessions. A stored document collection alone does not provide a complete personal memory system. ## Three kinds of context | Context | Typical purpose | | -------------------- | --------------------------------------------------------- | | Recent conversation | The immediate exchange and unresolved topics | | Durable user profile | Explicit preferences, names and approved personal context | | Character knowledge | Background information the character can retrieve | Keep each source identifiable so the application can update or remove the right information. ## Recommended data flow 1. Resolve the authenticated user, workspace and character. 2. Load recent messages and permitted profile facts. 3. Retrieve relevant character knowledge when needed. 4. Generate the response with that bounded context. 5. Summarize or analyze the completed exchange. 6. Save approved updates through the application's memory policy. ## Isolation and control Scope memory by workspace, user and character. A user's private conversation must not become another user's context. Support correction, deletion and retention settings in your product design. Avoid treating every generated assumption as a verified user fact. Preserve unknown values until the conversation supplies usable information. ## Configuration service We help define profile fields, summary behavior, retrieval rules, storage and lifecycle settings for your deployment. Persistence, access controls and retention are implemented and verified as part of that project scope. [Discuss a memory configuration](mailto:amora@amora.cam?subject=Persistent%20memory%20configuration). --- # Knowledge & analysis Source: https://amora.cam/docs/knowledge Give a character a curated body of information and use conversation analysis to produce structured summaries or profile updates. ## Knowledge ingestion A typical workflow creates a knowledge collection, imports approved files or URLs, extracts text, optionally rewrites it for retrieval, and indexes the processed content. Ingestion and indexing can be asynchronous. Track processing states before allowing a collection to influence production conversations. A successfully uploaded file is not necessarily ready for retrieval. ## Retrieval context Retrieve a bounded set of relevant passages for the current interaction. Preserve source identifiers so answers can be traced back to their context. Scope collections to the correct character and customer workspace. ## Conversation analysis Analysis can produce a conversation summary, sentiment feedback, custom metrics or proposed profile updates. Define the schema around the product decision the output will support. ```json { "summary": "A short factual summary of the exchange", "profile_updates": { "preferred_name": null, "favorite_topics": null } } ``` This is an example application output shape, not an Amora endpoint response contract. ## Budgets and retention Agree ingestion limits, processing budgets, supported files and output retention before launch. Copy any result that your application must retain into your own approved storage rather than assuming temporary job output is permanent. --- # Character configuration Source: https://amora.cam/docs/characters A character combines a recognizable identity with a clear role in your product. Configure the persona, voice, visual references and memory behavior as one system. ## Character brief Prepare the intended name, presentation, language, tone, conversation goals, boundaries and audience. Include example dialogue and visual references that communicate the experience you want. ## Runtime configuration Define identity instructions, personality, response style, roleplay behavior, knowledge access and tools. Keep product actions, such as opening a purchase flow, explicit and controlled by your application. ## Voice and visual identity Pair the character with an approved [voice configuration](/docs/voice-management). Add [Custom Character LoRA](/docs/custom-lora) when a consistent face and body are required across scenes and content assets. See [One character, any scene](/#characters) for Amora's visual examples. ## Localization and channels Plan localization around the intended language and market rather than translating only the interface labels. Validate voice, dialogue style and commercial flows on the website, mobile web experience and Telegram Mini App. ## Acceptance review Review sample conversations, knowledge accuracy, memory continuity, voice quality and visual consistency before publishing a character. Version approved configurations so later changes can be evaluated and rolled back. --- # Custom Character LoRA Source: https://amora.cam/docs/custom-lora **Custom Character LoRA** gives a character a dedicated visual identity that can be used across a content workflow. The service is available with a platform deployment or as a standalone project. ## One character, any scene The aim is a recognizable face and body across scenes, outfits and lighting. The [character gallery](/#characters) shows Amora in four different settings. A trained identity is one component of the generation workflow. Model choice, reference inputs, scene prompts and review still affect the final result. ## Example training dataset A character dataset can use approximately **50 curated images**, for example: | Frame type | Example share | | ---------------- | ------------- | | Portrait | 50% | | Full body | 30% | | Mid-body upwards | 20% | Vary angles, lighting, expressions and composition while keeping the intended identity consistent. The final dataset and training approach are tailored to your character and selected model. ## Service workflow 1. Agree the character brief and intended uses. 2. Prepare an AI-designed or approved creator-based reference set. 3. Curate the dataset and review identity consistency. 4. Train and evaluate the dedicated character model. 5. Configure generation recipes for agreed scene types. 6. Connect the approved workflow to your content operations. ## Content applications Use the character identity in photo sets, generated clips, paid-content catalogs and social-content workflows. Video generation may require a reference image produced by the character workflow rather than accepting a LoRA directly. [Request Custom Character LoRA](mailto:amora@amora.cam?subject=Custom%20Character%20LoRA). --- # Image & video generation Source: https://amora.cam/docs/content-generation Content generation turns a configured character identity into reviewable assets for the marketplace, conversations and distribution channels. ## Image workflow Start with the character identity or approved references. Submit a scene and composition brief, generate candidate images, review identity consistency, and store approved outputs with their associated character and content metadata. ## Generated video workflow Generated clips are asynchronous jobs. A typical workflow starts with an approved character image, submits an image-to-video request, tracks completion through a job status or webhook, and imports the result into the asset library. Retain the provider job identifier. A timeout does not prove that a paid job failed, so check its state before submitting it again. ## Asset lifecycle ```text Character + approved scene brief → Generation job → Status or webhook → Review and approval → Private asset storage → Publish to an entitled user or approved channel ``` Keep access controls and delivery URLs separate from generation. A temporary provider output URL is not a long-term content library. ## Media integrations Our [media provider guide](/docs/media-providers) recommends FLUX.2 for character imagery, Kling through fal for generated clips, and Runway as an alternative video integration. These are proposed integrations until connected and tested for the project. ## Live video streaming Live video-avatar streaming is **Coming soon**. It is a separate capability from generating and delivering a finished clip. --- # Media provider guide Source: https://amora.cam/docs/media-providers Select media services around the character workflow, supported content, rights and operational requirements of the project. The providers below are **recommended integration options**, not already-enabled Amora customer endpoints. ## Character images — FLUX.2 Black Forest Labs' FLUX.2 offers image generation and reference-based editing with a focus on consistent subjects. Evaluate it for character photos, scene variations and approved reference workflows. - [FLUX.2 model information](https://bfl.ai/models/flux-2) - [Developer terms](https://bfl.ai/legal/developer-terms-of-service) Custom LoRA workflows require a model and commercial arrangement that support that training and deployment approach; a hosted image endpoint does not automatically accept a custom LoRA. ## Generated clips — Kling through fal Kling image-to-video models on fal provide asynchronous generation and model-specific controls. Build around the queue, job status and webhook pattern, with server-held credentials. - [Kling image-to-video API](https://fal.ai/models/fal-ai/kling-video/v3/pro/image-to-video/api) - [fal acceptable-use policy](https://fal.ai/legal/acceptable-use-policy) fal's published policy prohibits sexually explicit content. Use this option only for content permitted by its policy and the selected model's terms. ## Alternative video — Runway Runway provides API-accessible video-generation models. Evaluate the available model catalog and request format for your scene types, reference inputs and output requirements. - [Available API models](https://docs.dev.runwayml.com/guides/models/) - [Runway API documentation](https://docs.dev.runwayml.com/) ## General and adult-oriented routes General-audience and explicit-content workflows cannot be assumed to use the same providers. Explicit-content generation requires a separately validated provider and model arrangement that permits the intended content and commercial use. Keep provider selection behind your backend integration. Unsupported requests should receive a clear result rather than silently being routed to a service that does not permit them. ## Production evaluation Test identity consistency, supported input formats, generation latency, cancellation behavior, job recovery, storage needs and actual cost. Provider prices, model versions and terms are checked again when the integration is commissioned. Recorded provider review: **19 October 2026**. Final provider selection and usage pricing are confirmed in the project scope. --- # Mobile & Telegram Mini App Source: https://amora.cam/docs/mobile Add a branded **mobile web experience and Telegram Mini App** alongside your website. This is an additional deployment feature scoped around the product and channels you want to operate. ## Mobile web Use the same character systems and backend integration with a touch-friendly presentation. Adapt navigation, portraits, content delivery and call controls to smaller screens and device safe areas. Provide a visible voice preview before microphone permission is needed. Handle interrupted playback, backgrounding and network changes explicitly. ## Telegram Mini App The Mini App can act as another entry point to the same character ecosystem. Integrate identity, entitlement checks, deep links and the relevant Telegram launch context on the backend. Review Mini App behavior in the intended Telegram clients as well as the ordinary browser experience. ## Shared identity and memory Agree how a user is linked across web and Telegram. Do not merge conversations merely because display names or contact details look similar. Use an explicit account-linking design before sharing memory or paid entitlements across channels. ## Voice on mobile - Serve the experience over HTTPS. - Request microphone access after an explicit call action. - Show permission-denied and device-unavailable messages. - Keep mute and hang-up accessible during the call. - Release microphone resources when the call closes or the page exits. - Stop recorded previews before live audio begins. ## Request the mobile feature [Contact our team](mailto:amora@amora.cam?subject=Branded%20mobile%20web%20and%20Telegram%20Mini%20App) with the desired channels, branding, identity flow and launch scope. Review the [live Mini App entry point](https://t.me/amora_callbot) for the existing Amora experience. --- # Commerce & monetization Source: https://amora.cam/docs/commerce The business layer connects character experiences to products, entitlements and payments. We scope commerce around your audience and operating model. ## Revenue models | Model | Typical implementation | | ------------------ | --------------------------------------------------------------------- | | Subscriptions | Membership access and recurring entitlements | | Voice calls | Metered usage or allocated conversation minutes | | Paid content | Photos, generated clips and voice messages | | Creator cloning | Creator-based characters with agreed commercial terms | | Companion commerce | Product discovery and explicit purchase journeys inside conversations | ## Entitlements before delivery Authenticate the user and verify the relevant subscription, balance or purchase before delivering a paid experience. Keep billing decisions on the server. A visible interface state alone must not grant access. ## Payments and reconciliation Agree the payment gateway, supported regions, webhook verification, order states and reconciliation process before launch. Retried payment events must not grant the same credit or content more than once. ## Companion-led commerce A character can suggest relevant products and open a product or checkout flow. The purchase itself remains an explicit user action handled by your commerce system. Product catalog access and available actions are configured for the deployment. ## Marketplace scope Catalog structure, creator onboarding, content storage, payment processing and operational responsibilities are agreed in the white-label or integration project. This documentation describes the architecture; it does not expose a public generic orders or billing API. --- # White-label deployment Source: https://amora.cam/docs/white-label Choose a full platform deployment, an integration into an existing product, or a regional operating partnership. ## White-label platform A branded AI companion marketplace configured for your audience. The project can include character configuration, Custom Character LoRA, web presentation, marketplace integration and an agreed operating environment. **Indicative deployment price: from $6,900**, followed by hosting and support. A typical agreed pilot targets approximately **two weeks / 80 engineering hours** after scope, access and assets are ready. These are planning terms, not a guaranteed delivery date for every project. Add [mobile web and Telegram Mini App](/docs/mobile) as an additional feature. Hosting can be provided by our team or installed on the infrastructure agreed for the project. ## API and integration For products that already have an audience, we help integrate the selected character, voice, memory and content capabilities. Our team handles the agreed integration work, technical configuration and handover. | API plan | Monthly starting price | | -------- | ---------------------- | | Starter | $100 | | Standard | $300 | | Scale | $900 | Prices are in USD. Usage allowances, overages and additional services are confirmed before activation. The public documentation remains a technical preview until your production access is arranged. ## Regional partnership The indicative split is **70% partner / 30% Amora**, subject to an agreement. The partner leads traffic, distribution, payment processing and local operations; Amora provides the agreed technology stack, hosting and updates. Regional scope and any exclusivity are negotiated individually. Target-market discussions include the USA, Japan, Korea, China and India. ## AI influencer cluster A separately scoped service for a coordinated character and content ecosystem. Indicative pricing is **$30,000 setup + $10,000/month** for ongoing ecosystem maintenance. Account operations, distribution and the content scope are agreed in advance. Financial forecasts are discussed privately in the sales process and are not guaranteed business outcomes. ## Next steps 1. Intro call and live demonstration. 2. Technical walkthrough and architecture review. 3. Choose a commercial model and agree responsibilities. 4. Scope, configure, test and launch the pilot. [Discuss your deployment](mailto:amora@amora.cam?subject=Amora%20white-label%20deployment). --- # Installation & operations Source: https://amora.cam/docs/operations Configuration, installation, DevOps and consulting are available as individual services or within a broader deployment engagement. ## Installation and deployment Agree the environment, domain, service configuration, credentials, storage and operational responsibilities before installation. Separate application code from runtime secrets and preserve a known working release for rollback. For Amora's own website, the established release path is a production branch, automated checks, a container image and deployment on the existing hosting infrastructure. ## Configuration services We configure character behavior, expressive voice, memory, knowledge context and enabled channels. LoRA training and content-generation workflows are scoped around the character and selected providers. ## DevOps and maintenance Services can include hosting, monitoring, incident investigation, updates, backups and deployment support. Agree response expectations, maintenance windows and responsibilities in the service scope. Track application health separately from provider health. A working marketing page does not establish that every voice, payment or generation service is currently healthy. ## Launch verification Check the branded entry points, authentication and entitlement flow, voice preview, live-call lifecycle, character imagery, mobile experience and error behavior. Confirm analytics do not collect raw credentials or private conversation content unintentionally. Validate backups and rollback procedures before treating a new environment as production-ready. ## Consulting Book architecture reviews, integration planning, workflow design or a technical audit. Bring your existing stack, user flow and launch constraints so the session can resolve concrete implementation decisions. [Request installation, DevOps or consulting](mailto:amora@amora.cam?subject=Amora%20installation%20DevOps%20and%20consulting). --- # Errors & usage Source: https://amora.cam/docs/errors-and-usage Handle failures according to the operation that failed. A playback error, an interrupted network request and an exhausted commercial allowance need different responses. ## User-facing failures | Situation | Recommended behavior | | ---------------------------- | --------------------------------------------------------------- | | Preview playback fails | Keep the page usable and offer explicit retry | | Microphone permission denied | Explain how to allow access; do not create the live call first | | Call still connecting | Prevent duplicate starts and allow cancellation | | Network interruption | Show connection state and apply the configured reconnect policy | | Generation outcome unknown | Check the existing job before submitting again | | Service unavailable | Keep a clear fallback and provide a support path | Show concise Amora-branded messages. Keep raw service URLs, keys and internal errors out of the visible interface. ## Status and retry behavior Production endpoints return the status codes and error shape agreed in your integration contract. Treat authentication failures as configuration issues, validation failures as request issues, and temporary service failures as potentially retryable only when the operation's outcome is known. Do not retry a paid call or generation blindly after a timeout. Retain its session or job identifier and reconcile status where supported. ## Usage and commercial limits The public API plans start at $100, $300 and $900 per month. Included usage, overage rates, supported concurrency, storage and service-specific allowances are confirmed during sales. There is no published universal requests-per-second guarantee in this technical preview. Rate limits and production capacity are agreed for the enabled services. ## Support details When reporting an issue, include the time, application environment, request or session identifier, operation and observed result. Remove keys, signed-link query strings and private user content before sharing logs. [Contact amora@amora.cam](mailto:amora@amora.cam?subject=Amora%20integration%20support).