Retell AI vs Voiceflow: Phone-First Agent or Support Platform

Retell AI and Voiceflow are both hosted, closed-source platforms. Retell is phone-first, at $0.07 to $0.31 a minute, with 20 calls at once included. Voiceflow runs one support agent across chat, phone and SMS, with a $0.05 phone minute plus credits. For code you can run yourself, there is Dograh, an open-source, self-hostable voice agent platform.

Key Takeaways

• Retell's $0.07 to $0.31 covers the model, but Voiceflow's $0.05 phone minute does not.
• Retell's BAA is self-serve on pay-as-you-go, while Voiceflow arranges it through its security team.
• To run the platform on your own servers, self-host Dograh, which is open source.

This post is part of our guide to Voiceflow alternatives. The guide's section "Hosted voice platforms: Vapi, Retell, Bland, Synthflow" says Retell "prices AI voice agents at $0.07 to $0.31 a minute, starting with $0.055 a minute for its voice infrastructure." This post puts the two side by side on that price, plus every other point that changes a buying decision.

A phone-first platform and a support platform

Retell is built around phone calls, while Voiceflow is built around one support agent that also answers chat and SMS. Most rows below follow from that.

What a minute costs on each

Retell's range is the price of a whole AI voice agent minute, while Voiceflow's $0.05 is the phone minute before speech, voice and model credits.

Retell's pricing page puts AI voice agents at $0.07 to $0.31 a minute. That starts with $0.055 a minute for Retell's voice infrastructure, with the language model billed per minute on top and Retell's telephony at $0.015 a minute, so the model you pick moves you along the range. Add-ons are priced per minute too: a knowledge base adds $0.005 and PII removal adds $0.01. Past 20 calls at once, each extra line costs $8 a month.

On Voiceflow, $0.05 is the phone usage charge on self-serve plans. Voiceflow's billing page says a bill is "made up of a monthly plan fee, optional add-ons like editor seats and phone numbers," plus credit-based usage. Speech-to-text minutes, voice characters and model tokens each use credits on top, at a rate set by the provider and model, and auto top-ups can buy more credits when the balance hits zero.

By our arithmetic, 10,000 minutes a month on Retell come to $700 to $3,100 before add-ons. On Voiceflow the phone usage alone comes to $500, before speech, voice and model credits and the plan fee. The two only compare once you price Voiceflow's credits for the same models. Our breakdowns of Retell AI pricing and Voiceflow pricing price every line.

Models and building an agent

Retell bills a list of models by the minute and sells speech-to-speech, while Voiceflow has you pick each layer from its provider list.

Retell prices each language model per minute, from small, cheap models to large ones. It also sells OpenAI's realtime speech-to-speech models, where one model takes the caller's audio in and sends speech back, at $0.07 to $0.38 a minute. Agents start as a single prompt, which Retell recommends unless you need more structure, or a Conversation Flow, where nodes each carry their own instructions and edges set when the call moves on.

Voiceflow has you choose speech-to-text from Deepgram, Gladia, Cartesia, AssemblyAI or Google, and voices from ElevenLabs, Cartesia, Rime, Google, Amazon or Microsoft. For the language model, its pricing page says to "choose from the biggest LLM providers, or bring your own model," and Voiceflow Core is its own. An agent combines a global prompt with playbooks for goals and workflows for fixed steps. Native Zendesk, Salesforce, HubSpot and Shopify tools come ready to use, and a traffic split sends a share of traffic to each version of the agent for A/B tests.

A support team that already lives in Zendesk or Salesforce gets further on day one with Voiceflow's native tools. A team that builds mostly phone flows will find Retell's Conversation Flow closer to the call itself.

Open Source Alternative to Vapi / Retell

Self-hosted voice agent platform — no per-minute fees

dograh-hq/dograh

Star on GitHub

Phone numbers, outbound calls and transfers

Retell sells numbers, outbound tools and several transfer modes, while Voiceflow's own numbers answer calls but can't place them.

Retell numbers cost $2 a month, and Retell charges nothing for SIP trunking or your own telephony. For outbound lists, batch calls are an add-on at $0.005 a dial, and branded caller ID costs $0.10 per outbound call. To hand a caller to a person, Retell's transfer docs offer three modes: a cold transfer, where the agent drops off at once; one where the agent stays on to brief the person or introduce the caller; and one where a separate AI agent screens the destination before connecting.

Voiceflow can provision one US or Canadian number per workspace with your plan, with more as an add-on, and you can connect your own Twilio, Vonage or Telnyx number. Voiceflow phone numbers currently don't support outbound calling, so outbound calls go out through your own carrier's number, one API request per call. To reach a person, the Call forward step transfers the caller to a phone number, an international number or a SIP address.

HIPAA, hosting and certificates

Retell lets any pay-as-you-go customer sign its BAA, while Voiceflow arranges its BAA through its security team.

Retell's compliance page says its business associate agreement (BAA) is available for self-signing. A signed BAA is required before any patient data passes through Retell. Voiceflow "supports HIPAA-compliant deployments," and asks you to contact its security team about the BAA for your use. Generally, whichever vendor signs, a BAA hands it obligations while your own HIPAA duties stay with you; confirm your position with counsel.

On hosting, Retell runs on its own cloud, and its Enterprise plan adds a dedicated stable server. The same compliance page says "we do not currently operate services within the European Union." Voiceflow's pricing page says "All hosted on Voiceflow," and its billing page lists private cloud hosting on Enterprise. Both are closed source.

For certificates, Retell lists SOC 2 Type 1 and Type 2, and Voiceflow lists SOC 2 Type II, ISO/IEC 27001:2022 and GDPR. Both sell personal-data removal as an extra: Retell's PII removal is $0.01 a minute, and Voiceflow's PII redaction add-on comes through its sales team.

Retell AI vs Voiceflow: picking between them

Pick Retell if phone calls are the whole job, especially if you want 20 calls at once from day one or a speech-to-speech model. Pick Voiceflow if one agent has to answer on chat and phone, or your support team relies on its native helpdesk and CRM tools.

Outbound-heavy teams on Voiceflow need their own carrier number for every outbound call. Teams weighing another hosted option can read Vapi vs Voiceflow and Synthflow vs Voiceflow.

Run the same call script on both over a real phone line before you sign. Most phone calls still reach the agent as 8 kHz audio, while a browser demo runs at 16 kHz, so a demo that sounds sharp can mishear callers on the phone.

Where an open-source platform fits

Both are hosted and closed source, and each decides where your calls run. Retell keeps them on its own cloud, outside the EU, and Voiceflow keeps them on its own, with private cloud on Enterprise. Neither lets you install the platform on servers you choose without a vendor contract, and that is where Dograh fits.

Dograh is open source under BSD-2-Clause, and its GitHub repository, with more than 5,900 stars, holds the whole platform. Its visual workflow builder joins nodes with pathways, each with a written condition the AI reads to pick its route, so a team used to Conversation Flow will find the idea familiar.

Dograh is the orchestration layer: it runs the call flow, tools and telephony, and the speech and language models are a separate layer you choose. That can be Dograh's own models, any supported provider on your own key, or open-weight models you host, and speech-to-speech models run too. Self-hosted, Dograh runs where you install it, such as an EU data centre. The call audio stays in-house only when the speech and language models run on your own servers too.

Dograh starts every account on its own managed models. To keep call audio away from Dograh, open Models, switch the Organization default to BYOK with your own speech and language providers (or local models), and check that no agent has its own model override.

For patient calls, self-host Dograh. No BAA with Dograh is needed, because Dograh never sees the data. Your speech and language providers may need their own BAA, and your phone carrier may too.

Your numbers stay with your carrier, such as Twilio, Vonage, Plivo or Telnyx. Transfer Call works on Twilio, Telnyx and Asterisk ARI. It passes no summary by default; on Twilio it can play a short spoken introduction to both people. Write the details to your system with an HTTP API tool before the transfer. Dograh is built for phone calls and also offers a text chat widget for websites, though teams whose main channel is text chat may prefer Voiceflow.

Self-hosted Dograh has no per-minute platform fee (servers, model keys and phone minutes still cost); Dograh Cloud has a 1¢-a-minute platform fee, with 10 concurrent calls included. Self-hosting puts uptime in your team's hands, and there is no one-click import from Retell or Voiceflow, so each agent is rebuilt.

Dograh is the strongest fit when you want to pick the servers and the models yourself, without a vendor contract, because the code is yours to run. To try it, self-host it with Docker Compose, or start on Dograh Cloud.