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.

Vapi vs ElevenLabs: AI voice agents compared

Updated 2026-07-14

Vapi and ElevenLabs sit at opposite ends of the build-versus-buy line. Vapi is an orchestration layer: it ties together transcription, a language model, text-to-speech, and telephony behind one API, lets you choose the provider for each, and passes those costs through at cost, or free with your own API keys, on top of a $0.05 per minute hosting fee. ElevenLabs ships an integrated voice-first stack instead, with its own text-to-speech, 70+ languages, and RAG built into every subscription tier, sold as bundled monthly minutes with $0.08 overage. The two are not purely rival: Vapi can use ElevenLabs as its text-to-speech provider, so the real question is whether you want to assemble the pipeline yourself for control, or buy the integrated one for speed. Pricing verified July 2026.

Pricing side by side

	Vapi	ElevenLabs
Model	Orchestration, bring your own stack	Integrated voice-first stack
Pricing	$0.05/min hosting + components at cost	Subscription tiers; $0.08/min overage
Free to start	60+ minutes	Free 15 min/mo
Voice and model choice	Any provider, incl. ElevenLabs voices	ElevenLabs voices; LLM passed through
Languages	Depends on chosen providers	70+ built in
Knowledge base / RAG	Via chosen providers	Built in, all tiers
Concurrency	10 lines (+$10/mo each)	4 to 40 by tier

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

Assemble it or buy it

Vapi gives engineers a clean API and full control: pick the transcription, the model, the voice, and the telephony, tune each one, and pay providers directly with no markup. That control is the reason to choose it, and the reason it takes longer to stand up. ElevenLabs removes those decisions. The voice, language coverage, and retrieval come integrated, so you configure an agent rather than wire a pipeline, in exchange for less say over each layer.

They can also work together

This is not a strict either-or. Because Vapi supports ElevenLabs as a text-to-speech provider, a common setup is Vapi for orchestration with ElevenLabs voices inside it. If you want ElevenLabs voice quality but also want to control the model and telephony, that pairing gives you both. You would pick ElevenLabs directly when you want the whole stack, including RAG and multi-channel delivery, handled in one place.

Which to choose

Choose Vapi when a team wants to compose and control the voice stack and keep provider costs transparent. Choose ElevenLabs when you want a turnkey multilingual voice agent with RAG and WhatsApp or web delivery built in, and less assembly to reach production.

The visual gap

Both are audio-only, so neither shows the caller anything. When the agent needs an email, a date of birth, or a card number, the caller spells it out and hopes the transcription holds. Powsoo renders a tap-to-confirm card in the browser during the call, the caller taps the right value, and a webhook returns it clean. It runs on both Vapi and ElevenLabs. See the data-capture guide, or read Retell vs Vapi and Retell vs ElevenLabs.

Frequently asked questions

Can I use ElevenLabs voices with Vapi?

Yes. Vapi supports ElevenLabs as a text-to-speech provider, billed at provider cost. Choosing Vapi does not mean giving up ElevenLabs voice quality; it means wiring it in yourself alongside your chosen transcription and model.

Which needs less engineering?

ElevenLabs. It ships the pipeline and RAG integrated, so there is less to assemble. Vapi expects you to select and connect each provider, which is the point of its flexibility but adds setup.

Do either display fields to the caller on screen?

No. Both are voice-only. A visual layer such as Powsoo adds synced on-screen cards to either, so callers tap to confirm rather than spelling values out loud.