How to get picked for voice agents by coding agents
Vapi took 24% of 308 judged voice agents sessions. What the numbers say a vendor in this category should do.
If you sell voice agent platforms, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for voice agents and never compares vendors.
The numbers come from 308 judged sessions with Claude Code, Codex and Cursor, spread across 10 realistic codebases, with every session read by a judge.
What coding agents choose for voice agents
Across 308 judged sessions, Vapi was chosen most often, in 24% of runs. Retell AI was second with 18%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Vapi | 74 | 24% |
| 2 | Retell AI | 55 | 18% |
| 3 | OpenAI Realtime API | 37 | 12% |
| 4 | LiveKit Agents | 35 | 11% |
| 5 | ElevenLabs Agents | 30 | 10% |
| 6 | Twilio ConversationRelay | 28 | 9% |
| 7 | Built in-house (no product adopted) | 18 | 6% |
| 8 | Azure Voice Live API | 10 | 3% |
| 9 | Cartesia Line | 5 | 2% |
| 10 | Picovoice | 4 | 1% |
Full board, every run replayable: the voice agents leaderboard.
What the shape of this category means
The leader takes only 24% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 24%, voice agents is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 94 | Twilio ConversationRelay (23) |
| Codex | 110 | OpenAI Realtime API (32) |
| Cursor | 104 | Vapi (41) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's voice agents sessions and almost none of Claude Code's. Taking OpenAI Realtime API's position with Codex is a content problem. Taking Twilio ConversationRelay's with Claude Code is a repository problem.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 62 | Vapi |
| Junior developer | 42 | Vapi |
| Senior engineer | 128 | Vapi |
| Enterprise team | 76 | LiveKit Agents |
That is 2 different products winning voice agents for 4 kinds of buyer, out of the same 308 sessions. Nobody here is winning voice agents. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 6% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In voice agents the clearest case is Synthflow AI: on the table in 58 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Synthflow AI | 58 sessions | 0 |
| Bland AI | 52 sessions | 0 |
| Amazon Connect | 47 sessions | 0 |
| Voiceflow | 24 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 181 sessions is recorded in each transcript, one reason at a time.
What to do about it in voice agents
- Treat the ordering as movable. The leader holds 24%, so agents are deliberating rather than defaulting, and the inputs they use can change the answer. This is the most winnable shape a category comes in.
- Pick which buyer you are for. The same voice agents need written as a vibe coder landed on Vapi, and written as an enterprise team landed on LiveKit Agents. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
- Measure per agent. Claude Code put Twilio ConversationRelay first, Codex put OpenAI Realtime API first, Cursor put Vapi first. A blended number for voice agents describes a market that does not exist.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every voice agent platform on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Vapi? — chosen in 24% of sessions
- Do coding agents recommend Retell AI? — chosen in 18% of sessions
- Do coding agents recommend OpenAI Realtime API? — chosen in 12% of sessions
- Do coding agents recommend LiveKit Agents? — chosen in 11% of sessions
- Do coding agents recommend ElevenLabs Agents? — chosen in 10% of sessions
- Do coding agents recommend Twilio ConversationRelay? — chosen in 9% of sessions
- Do coding agents recommend Azure Voice Live API? — chosen in 3% of sessions
Where these numbers come from
308 judged sessions in voice agents across 10 codebases, part of a published set of 5,292. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every voice agents run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
308 judged sessions across 10 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What voice agent platform do coding agents choose?
Across 308 judged sessions, Vapi was chosen most often, in 24% of runs. Retell AI was second with 18%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same voice agent platform?
No. Claude Code picked Twilio ConversationRelay, Codex picked OpenAI Realtime API, Cursor picked Vapi. Measuring one agent tells you about part of the market only.
How often do agents build voice agents themselves instead of installing something?
In 6% of runs the agent wrote the code itself rather than adopting a product.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which voice agent platforms do agents consider but never choose?
Synthflow AI (raised in 58 sessions, chosen in none), Bland AI (raised in 52 sessions, chosen in none), Amazon Connect (raised in 47 sessions, chosen in none), Voiceflow (raised in 24 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
Where this comes from
Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.