Voicebun
Pratham Hombal (Stratify AI) · Voice & Language
Voicebun is an AI voice agent builder that turns a plain-English description into a working voice assistant. It adds voice cloning, real-time calls, and phone numbers, with plans from $0 to $20/mo.
About Voicebun
What Is Voicebun
Voicebun is a voice agent builder and AI voice assistant platform. You describe the agent you want in ordinary text, such as "a language tutor that practices conversational Spanish," and the platform configures a real-time voice assistant that matches. It's aimed at people who want a talking agent without wiring up speech models, telephony, and a backend themselves.
The product is open source under the Apache 2.0 license, which sets it apart from most closed voice platforms. Developers can read the code, self-host it, and see exactly how agents are assembled from LiveKit, OpenAI, and Supabase. The hosted version handles the setup so you don't have to.
The main limits are scale and maturity. It's a young project from an independent maker, the free tier caps you at 5 call minutes a month, and the deeper phone features sit behind the paid plan. If you need enterprise telephony guarantees, the paid tiers and the Enterprise plan cover that, but the project isn't built for heavy regulated workloads out of the box.
Getting Started
- Create an account with an email and password or by signing in with Google.
- Describe your agent in plain English, naming the role and the tone you want.
- Pick or clone a voice for the agent to speak with.
- Test the agent in the browser over a real-time call and adjust the description until it sounds right.
- Provision a phone number and publish the agent to take live calls.
Product Information
A quick look at Voicebun's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Small business owners
- Solo makers and tinkerers
- Language learners and tutors
Tasks
- Building a customer support agent
- Cloning a brand voice
- Prototyping a voice idea
Scenarios
- Testing a support concept before launch
- Handling overflow calls at a small shop
- Practicing a new language
Key features
Prompt-to-Agent Builder
You write what you want in plain English and Voicebun turns it into a configured voice agent. There's no drag-and-drop flow to learn and no model settings to tune by hand. The agent arrives ready to talk, and you refine it by editing the description rather than editing code.
Real-Time Voice Conversations
Agents hold low-latency, two-way conversations rather than reading a script. That matters for support calls and tutoring, where the agent has to listen, respond, and handle interruptions like a person would. The real-time voice layer runs on LiveKit, which powers the audio transport.
Voice Cloning
Beyond preset voices, Voicebun supports cloning so an agent can speak in a specific voice you choose. The free plan already includes unlimited voice cloning, which is unusual at the entry tier. It helps small teams keep a consistent vocal identity across every agent they deploy.
Phone Number Provisioning
Agents can be assigned real phone numbers to take live calls. The free plan includes one number, the Professional plan includes five, and Enterprise offers unlimited numbers. That turns a browser demo into something customers can actually dial.
Open-Source, Self-Hostable Code
The codebase is on GitHub under Apache 2.0, built on Next.js, Supabase, LiveKit, and OpenAI. If you'd rather run it yourself, you can clone the repo, add your own API keys, and host your own instance. This is the biggest gap between Voicebun and closed rivals.
Community Agent Gallery
Voicebun hosts a public gallery of agents built by other users, grouped by category like healthcare, education, customer service, and productivity. You can browse working examples and their descriptions, which shortens the blank-page problem when you're starting a new agent.
Pros and cons
Pros
- Build a working voice agent from a plain-English description
- Voice cloning is included even on the free plan
- Open-source code under Apache 2.0, so you can self-host
- Phone number provisioning turns demos into real callable agents
- Clear pricing at Free, $20/mo Professional, and custom Enterprise
Cons
- The free plan caps you at 5 call minutes a month
- Overage runs about $0.05 a minute on paid plans
- Running it yourself means supplying your own OpenAI, LiveKit, and Supabase accounts
- It's a young project, so enterprise-grade telephony and compliance aren't fully established
Frequently asked questions
Voicebun is an open-source voice agent builder, a no-code voice agent builder for everyday users, and an AI voice assistant platform. You describe an agent in plain English, and it configures a real-time voice assistant that can clone a voice, take live calls, and run on a provisioned phone number.
Related content
Explore related tools, skills, and articles for Voicebun.
Voicebun Alternatives
Prosp
Prosp · Writing · Voice & Language · MarketingProsp is an AI LinkedIn outreach tool built for agencies and sales teams, and it writes the message and the voice note in your own voice for each prospect so they actually reply. You connect your accounts, find leads, and let the AI draft and send personalized messages at scale, all from one inbox. It's built for people running outbound at volume. That's the whole pitch. Every touchpoint still has to feel human.
Wordly AI Translation
Wordly · Voice & Language · ProductivityWordly AI Translation is a real-time AI translation and captioning platform built for meetings, conferences, and events. It delivers live translation, captions, transcripts, and summaries in more than 60 languages, and attendees join by scanning a QR code or opening a link instead of using dedicated headsets. The platform works with Zoom, Microsoft Teams, Google Meet, and Webex, and it's designed for organizations that want multilingual access without hiring human interpreters for every session. Simple as that.
Musicful
Musicful AI · Voice & Language · VideoMusicful is an AI music generator and AI music video maker that turns text to music in minutes. Give it a text prompt, a set of lyrics, or a hummed melody and it returns a finished track with vocals and instruments. It also doubles as an AI song generator, produces music videos from the songs you create, and offers an AI cover tool plus a developer API. The platform runs in a web browser and through an Android app, so you can start a song on desktop and pick it up on your phone.