Powsoo is a drop-in widget that adds visual intake cards to AI voice platforms. When a user is on a voice call with your agent, Powsoo renders synced cards in the browser so users can tap-to-confirm emails, phone numbers, dates, and other intake fields instead of spelling them out.

How do I add Powsoo to my voice platform?

Create a widget in the Powsoo dashboard and connect your Retell account, then drop one web component and one versioned script tag into your site. You add powsoo_show_card as a custom function on your agent. Setup takes about 5 minutes.

Which voice platforms does Powsoo support?

Retell today. Vapi and ElevenLabs support are coming soon. SMS fallback works for traditional PSTN calls.

Can I customize the look of the cards?

Yes. Powsoo supports full theming via JS configuration: colors, fonts, border radius, spacing. For deeper control, use Powsoo Atoms (React components) to build your own UI.

Where does the data go after a user confirms?

Powsoo fires webhooks the moment a card is confirmed, with the field name, value, and call session ID. Drop the payload straight into your CRM, database, or backend.

Does Powsoo work for phone calls?

Pure phone calls (PSTN) don't have a screen, so Powsoo's web widget can't render directly. Instead, Powsoo offers an SMS fallback: when the agent needs to confirm an email or phone number, the caller gets a one-tap SMS link.

Is Powsoo HIPAA / GDPR compliant?

Powsoo is built with healthcare and EU customers in mind. We're SOC 2 Type II in progress and offer DPAs and BAAs on the Pro plan and above.

Retell vs Vapi: which AI voice agent platform to pick

Updated 2026-07-14

Retell and Vapi solve the same job two opposite ways. Retell is an opinionated, all-in-one voice-agent platform: it bundles speech-to-text, the language model, text-to-speech, and telephony into one pipeline, adds a visual flow builder, and ships SOC 2 and HIPAA on the pay-as-you-go plan, so a team can put a compliant phone agent live in a day. Vapi is an orchestration layer: it hands you each part of the stack separately, so you choose your own transcription, model, voice, and telephony, and it passes provider costs through at cost, or at no charge when you bring your own API keys. That makes Vapi the pick for engineers who want to swap and tune every layer, and Retell the pick for teams who want the pipeline handled for them. Both start near $0.05 per minute for the base engine, before model and telephony costs. Pricing verified July 2026.

Pricing side by side

	Retell	Vapi
Base engine	$0.055/min voice + $0.015/min TTS	$0.05/min hosting
Typical all-in per minute	$0.07 to $0.31, by model	Hosting + model/voice/telephony at cost
Model and voice choice	Bundled, swappable	Any STT, LLM, TTS; $0 with your own keys
Free to start	$10 in credits	60+ free minutes
Included concurrency	20 calls	10 lines (+$10/mo each)
SOC 2 and HIPAA	On pay-as-you-go, BAA available	Scale plan only
Visual flow builder	Yes	No, API-first

Rates verified July 2026. Check each provider for current pricing.

Where they differ

The split is convenience versus control. Retell decides the shape of the pipeline for you and exposes it through a flow builder and one framework, so most of the assembly is already done. It reports typical latency around 600ms and includes 20 concurrent calls before you pay for more capacity. Vapi does the opposite: it exposes transcription, model, voice, and telephony as separate choices behind one API, with SDKs for web, iOS, and JavaScript, and it marks up none of the provider costs. You trade setup time for the ability to tune or replace any layer.

Compliance is the other practical difference. Retell carries SOC 2 and HIPAA readiness on the pay-as-you-go plan and will sign a BAA. On Vapi, SOC 2, HIPAA, PCI, SSO, and data residency sit on the Scale plan, so a regulated workload starts higher up the pricing ladder.

Which to choose

Pick Retell if you want a compliant phone agent live quickly, prefer a visual builder to code, and are comfortable with a bundled pipeline. Pick Vapi if you have engineers who want to choose each model and voice, control cost with their own API keys, and treat the voice stack as something to compose rather than accept. Neither choice locks you out of the other later; the agent logic is portable in both.

Both are voice-only

Whichever you land on, the caller only ever hears the agent. When Retell or Vapi asks for an email address or a card number, the caller spells it out loud and the transcriber guesses. Powsoo adds the missing screen: during the call it renders a tap-to-confirm card in the browser, the caller taps the correct value, and a webhook returns it clean. It runs on both Retell and Vapi, so the visual layer is identical regardless of which platform you pick. See the data-capture guide for how that works, or compare the platforms from another angle in Retell vs ElevenLabs and Vapi vs ElevenLabs.

Frequently asked questions

Is Retell or Vapi cheaper?

The base fees are close: Retell's voice engine is $0.055/min and Vapi's hosting is $0.05/min. Real cost depends on the model and telephony you add on top. Vapi can come out cheapest because it charges STT, LLM, and TTS at provider cost, or free when you supply your own API keys. Retell bundles more, so there is less to assemble but fewer places to shave cost.

Which is better for a non-engineer?

Retell. Its visual flow builder and bundled pipeline mean you configure an agent without wiring separate providers. Vapi's flexibility assumes you want to compose the stack yourself through its API.

Do either show anything on the caller's screen?

No. Both are voice-first and neither renders on-screen confirmation. To let a caller confirm an email or a number by sight, you add a visual layer such as Powsoo on top of either platform.