Callia
The AI voice agent platform Vapi and Retell keep for themselves — owned once, white-labeled, and rebranded as yours.
Callia is a self-hosted platform for building AI phone agents. The platform owner deploys it, connects their own telephony, speech-to-text, text-to-speech and language-model keys, and their end-users create agents that handle business calls autonomously — inbound reception, outbound campaigns, appointment booking, lead qualification and support.
Swap the voice, the model or the carrier without rebuilding the agent.
Voice AI is assembled from other people's services, and each one is a hand on your margin. A telephony provider raises per-minute rates, a voice vendor changes its licensing, a model doubles in price — and a platform that hardcoded any of them passes the increase straight through to whoever is running the business. Agencies discover this at renewal, when the economics that justified the whole operation stop working and there is no way to move without rebuilding everything they have shipped to clients.
- Provider Configuration (5 layers)
Interruptions, transfers and after-hours calls behave the way callers expect.
Text assistants fail on the phone in ways that are obvious the first time a real customer calls. Someone interrupts mid-sentence and the agent keeps talking over them. Someone asks for a human and there is nowhere to go. Someone calls at nine at night and gets the same script as noon on Tuesday. Each one reads to the caller as a company that could not be bothered, and the business that bought the service hears about it from their own customers before they hear about it from anyone else.
- Inbound Calling
- Call Flow Designer (@xyflow voice nodes)
The check runs before the dial, not as a report afterwards.
Outbound calling carries a rule that everyone knows and most systems enforce too late: some numbers must not be called. A queue that dials first and reconciles later has already made the call by the time anyone notices, and the record of it exists. For the business running the campaign this is not a reporting inconvenience — it is the one part of outbound where being wrong is expensive, and it is the part cheap dialling tools are quietest about.
- Outbound Campaigns (real dial engine)
- Contact Management
Versioning with rollback matters more here than in most products: a prompt change that degrades an agent is discovered through calls that already happened with real customers, and the recovery has to be immediate.
A library of pre-built templates — receptionist, sales, support, appointment setter — is available from the entry tier.
The live chain runs speech recognition into the language model into speech synthesis, with three capabilities that separate a usable phone agent from a demo:
Do-not-call list management is available from the entry tier, since an outbound feature without it is a liability rather than a capability.
Voicemail detection, so an agent handles a machine differently from a person, is available on the higher tiers.
Calls are auto-tagged and exportable.
This is the surface an operator lives in after launch. Agent quality is not assessed from an aggregate score — it is assessed by listening to the calls that went badly, which requires being able to find them.
Per-contact history is what makes a second call intelligible: the agent knows this person called last week.
Two providers can be configured on a layer at once, so a swap is a toggle rather than a migration.
The connection test performs a real authenticated call to the provider rather than checking that a field is filled in. A key that is present and wrong is the failure mode that otherwise surfaces during someone's first live call.
Cost per provider is the number that makes the multi-provider design pay: it is what tells an owner whether the swap they are considering is worth making.
Voice cloning is available on the top tier, where the synthesis provider supports it.
The platform underneath the product — counted in this product's own source, not claimed from a template. Where a row carries a list, open it to read the names behind the number.
Hover a table to isolate what it touches; click one to read its relationships. The big nodes are what everything else hangs off. organizations is referenced by 53 tables because every single record in this product belongs to an organization, and that is what makes tenant isolation a property of the database rather than something the application has to remember on every query.
all 60 tables, as text
active_boosts · admin_notifications · agent_templates · agent_versions · agents · announcement_dismissals · announcements · api_key_logs · api_keys · audit_logs · automation_log · automation_templates · call_events · call_flows · calls · campaign_calls · campaigns · contacts · credit_balances · credit_transactions · currencies · data_exports · data_imports · dnc_list · faq_categories · faq_items · feature_flags · inbound_webhooks · kb_chunks · kb_documents · kb_misses · knowledge_bases · languages · notification_log · notification_rules · notifications · organization_limit_overrides · organizations · phone_numbers · plans · platform_secrets · platform_settings · product_purchases · products · provider_prices · push_devices · report_templates · roles · scheduled_tasks · subscriptions · theme_page_sections · theme_section_library · theme_sections · translations · user_sessions · users · voice_library_cache · webhook_endpoints · webhook_logs · webhooks
The chassis, and anything particular to this product. 4 required, 3 optional.
No platform lock-in.
Postgres with row-level security and vector search for agent knowledge.
Supplied by the platform owner. Numbers are bought through it.
At least one of each layer. All five layers are the owner's own accounts.
Outbound dialling dispatches through it. Inbound calls are unaffected.
Deployed alongside the platform. Without it that one test mode reports a clear error; live calling is unaffected.
Call audio.
Already built — plug and play
Every provider integration in this list ships wired into the product. You bring your own keys, connect them in the admin, and go live — there is no integration code to write. Nothing is resold through us: the ongoing cost is whatever these providers charge you. Capabilities marked plan-gated elsewhere on this page unlock by plan, not by extra code.
What exactly do I receive after purchase?
The complete source repository behind the live demo — 125,509 lines across the application and its database, 60 tables defined by 52 migrations that the shipped scripts apply for you, plus the seed data, the demo accounts and the setup documentation. Not a subset and not a scaffold: the same code that runs the demo you just used.
Is the live demo the same product whose source I receive?
Yes. The Callia demo runs the delivered release (v1.0.0), and the build figures on this page are measured from that same source — not from a showcase build kept separately.
Can I test every account role before buying?
Yes — all 3 of them: Agent operator, Business owner, Platform admin. Each one is seeded in the live demo and reachable from the role board above, so you can inspect the product from the customer's side, the agent's side and the administrator's side before you decide.
Is this a complete product or a starter template?
Complete. 85 page modules and 263 HTTP operations, with authentication, roles, billing, an administration panel, background jobs and seeded demo data all wired and running. A template gives you the shape of an application; this is one you can deploy and start operating.
Can I rebrand and modify it?
Yes, without asking. The name, identity, copy, styling and code are yours to change. Rebranding and operating it as your own service is exactly what the licence is for.
What does the licence allow?
A perpetual, worldwide, non-exclusive, non-transferable licence to the product you bought and to every update released for it. The Standard licence covers one business — yours. If you deploy for clients, the Client licence covers up to five. You can modify it, rebrand it, deploy it and charge your own customers.
Can I resell the source code?
No. Reselling, redistributing, sublicensing or giving away the source itself is not permitted under either licence. You build and deliver products with it — the code stays with you.
What services and ongoing costs are required?
You bring your own accounts, so we never mark anything up and there is no ongoing cost to us beyond the purchase. Required: Node host, Supabase, A telephony account, Speech and language provider keys, A job queue, Relay component, Object storage. Optional: none. The table above says exactly what stops working without each one; most have usable free tiers at low volume.
How difficult is deployment?
Two ways, and most buyers use the first. The installer in your saascode dashboard walks it: you create free accounts at Vercel and Supabase, connect them, and it provisions the database, applies 52 migrations, seeds the data, deploys and verifies the result — you watch the steps go green. Or take the source and do it yourself with the shipped scripts and docs, which is the same sequence run by hand.
What updates and support are included?
Updates to that product for as long as we maintain it — no renewal fee and no expiry date on your access. Support covers download problems, defects in the code as shipped, questions about what the product does and how it is structured, and licence questions. It does not cover debugging your own modifications, building features for you, or setting up your hosting and third-party accounts.
Why does a complete codebase cost $349?
Because it was built once and is distributed many times. SaaSCode builds each product and ships the same finished release through the catalog, so the price reflects repeatable distribution — not a reduced codebase, an unfinished template, or what the same work would cost commissioned.
Do I need to be a developer?
No, for the normal path. You create free accounts at Vercel and Supabase, connect them to the installer in your saascode dashboard, and it does the deployment for you — provision, migrate, seed, deploy, verify. What it asks of you is creating two accounts and copying a token, not writing code. If you would rather deploy it yourself, or host it somewhere else, the full source and the scripts are yours to do that with. Running the product day to day needs no technical skill at all: that happens through its own interface, which is what the demo shows.
