Do coding agents recommend OpenAI Realtime API?
OpenAI Realtime API was chosen in 6% of 754 judged voice agents sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
OpenAI Realtime API was chosen in 6% of 754 judged voice agents sessions, ranking sixth. It was also raised as a candidate in 153 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in voice agents inside a realistic codebase. Not what a chat assistant says about OpenAI Realtime API. What an agent actually installed.
The numbers
| Category | Voice agents |
| Sessions in the category | 754 |
| Sessions where OpenAI Realtime API was chosen | 49 |
| Install share | 6% |
| Rank in category | 6 of 32 |
| Codebases it won in | 11 |
| Raised as a candidate, not chosen | 153 |
| Chosen when considered | 24% |
| Site | openai.com |
By agent
The agents treat OpenAI Realtime API very differently. Codex chose it in 16% of its sessions in this category and Claude Code in 1%, a spread of 15 points.
| Agent | Sessions | Chose OpenAI Realtime API | Share |
|---|---|---|---|
| Claude Code | 157 | 1 | 1% |
| Codex | 217 | 35 | 16% |
| Cursor | 167 | 5 | 3% |
| Grok Build CLI | 60 | 1 | 2% |
| Muse Code | 153 | 7 | 5% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 1%, not 6%.
By who was asking
OpenAI Realtime API performs similarly across the four kinds of buyer, from 4% to 9%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose OpenAI Realtime API | Share |
|---|---|---|---|
| Vibe coder | 134 | 6 | 4% |
| Junior developer | 90 | 8 | 9% |
| Senior engineer | 322 | 22 | 7% |
| Enterprise team | 208 | 13 | 6% |
What OpenAI Realtime API was up against
The full ranking in voice agents, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Retell AI | 168 | 22% |
| 2 | Vapi | 124 | 16% |
| 3 | Twilio ConversationRelay | 99 | 13% |
| 4 | LiveKit Agents | 98 | 13% |
| 5 | ElevenLabs Agents | 59 | 8% |
| 6 | OpenAI Realtime API (this page) | 49 | 6% |
| 7 | Built in-house (no product adopted) | 35 | 5% |
| 8 | Grok Voice Think Fast 2.0 | 29 | 4% |
What this means
This is an integration problem, not a presence problem. Agents raised OpenAI Realtime API in 153 sessions and chose it in 49, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 754 sessions in voice agents are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every voice agents run can be replayed on the board.
If you work on OpenAI Realtime API: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend OpenAI Realtime API?
Yes. OpenAI Realtime API was chosen in 49 of the 754 judged sessions in voice agents, a 6% install share, ranking sixth in its category.
Does Claude Code recommend OpenAI Realtime API?
In 1 of the 157 sessions in voice agents run with Claude Code, which is 1%.
Do different coding agents treat OpenAI Realtime API differently?
Yes, and by a wide margin. Codex chose it in 16% of its runs and Claude Code in 1%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is OpenAI Realtime API considered but not chosen?
It was raised as a candidate in 153 sessions without being chosen, and chosen in 49. That is a 24% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.