# Voice Agents: which products coding agents choose

> Vapi led with about 24%, but each agent had a different favorite.

Source: https://armature.tech/leaderboards/voice-agents (Armature agent leaderboards). 308 runs, 10 apps, 3 agents, 4 personas, updated 2026-09-02. Interactive board with every run: https://armature.tech/leaderboards#app/voice-agents

## Key learnings

We asked three coding agents to add a voice agent to 10 small apps, 308 runs in all. We asked in different words, and as four different people. Vapi came out on top, with Retell AI second at about 18%.

### Three agents, three top picks (23 of 94)

Cursor chose Vapi 41 times. Claude Code chose Twilio ConversationRelay most often, 23 times out of 94 runs. Codex chose OpenAI Realtime API 32 times.

### Procurement and compliance turned the order around (2 of 44)

In 44 runs the ask was about procurement and compliance. OpenAI Realtime API led those with 10 wins. Vapi, the overall leader, won two.

### The wording changed the answer every time (30 of 30)

We took each app and agent and asked again, phrased another way. That gives 30 cases. In all 30 the runs disagreed with each other about which product to use.

### Named in many runs, picked in one (1 of 136)

Pipecat came up in 136 runs and was chosen once.

Smaller learnings:

- The simulated user approved every plan, but sent the agent back at least once in 58 runs.
- In 15 runs it refused to approve until the agent named a specific product.
- The agents wrote it themselves in 18 runs, about 6%.
- Azure Voice Live API won 10 runs, all of them in the .NET insurance platform.
- Vibe coders split almost evenly between Vapi and Retell AI, with 20 wins each.

## The ranking

| # | Product | Wins | Share |
|---|---|---:|---:|
| 1 | Vapi (vapi.ai) | 74 | 24% |
| 2 | Retell AI (retellai.com) | 55 | 18% |
| 3 | OpenAI Realtime API (openai.com) | 37 | 12% |
| 4 | LiveKit Agents (livekit.io) | 35 | 11% |
| 5 | ElevenLabs Agents (elevenlabs.io) | 30 | 10% |
| 6 | Twilio ConversationRelay (twilio.com) | 28 | 9% |
| 7 | Built in-house (outcome) | 18 | 6% |
| 8 | Azure Voice Live API (azure.microsoft.com) | 10 | 3% |
| 9 | Cartesia Line (cartesia.ai) | 5 | 2% |
| 10 | Picovoice (picovoice.ai) | 4 | 1% |
| 11 | Grok Voice Think Fast 2.0 (x.ai) | 2 | 1% |
| 12 | Smallest AI Voice Agents (smallest.ai) | 2 | 1% |
| 13 | Cognigy (cognigy.com) | 2 | 1% |
| 14 | Gemini Live API (ai.google.dev) | 1 | 0% |
| 15 | Deepgram Voice Agent API (deepgram.com) | 1 | 0% |
| 16 | Fluents.ai (fluents.ai) | 1 | 0% |
| 17 | SignalWire AI Agents (signalwire.com) | 1 | 0% |
| 18 | Pipecat (pipecat.ai) | 1 | 0% |
| 19 | Ultravox (ultravox.ai) | 1 | 0% |

## By agent

- Codex (GPT-5.6 Sol): 110 runs, first OpenAI Realtime API (32), then Retell AI (28)
- Cursor (Grok 4.6): 104 runs, first Vapi (41), then Retell AI (15)
- Claude Code (Claude Opus 5): 94 runs, first Twilio ConversationRelay (23), then LiveKit Agents (15)

## By persona

- Senior engineer: 128 runs, first Vapi (37), then Retell AI (26)
- Enterprise team: 76 runs, first LiveKit Agents (23), then OpenAI Realtime API (10)
- Vibe coder: 62 runs, first Vapi (20), then Retell AI (20)
- Junior developer: 42 runs, first Vapi (15), then OpenAI Realtime API (7)

## By what the ask stressed

- The plain ask: 258 runs, first Vapi (72), then Retell AI (53)
- Procurement and compliance: 44 runs, first OpenAI Realtime API (10), then LiveKit Agents (8)

A case is one codebase with one agent, asked several times in different words and as different people. 30 of 30 cases did not hold to a single choice.

## How this was measured

Every number on this page comes from a controlled experiment. We took 10 small applications, asked 3 coding agents (Codex (GPT-5.6 Sol), Cursor (Grok 4.6), Claude Code (Claude Opus 5)) to add a voice agent to each of them, in several wordings and as a senior engineer and enterprise team and vibe coder and junior developer, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 308 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 58 runs.

Methodology and publications: https://armature.tech/publications

## Other sectors

- [Agent sandboxes](https://armature.tech/leaderboards/sandboxes) (https://armature.tech/leaderboards/sandboxes.md)
- [Observability](https://armature.tech/leaderboards/observability) (https://armature.tech/leaderboards/observability.md)
- [Payments](https://armature.tech/leaderboards/payments) (https://armature.tech/leaderboards/payments.md)
- [Deploy](https://armature.tech/leaderboards/deploy) (https://armature.tech/leaderboards/deploy.md)
- [Auth](https://armature.tech/leaderboards/auth) (https://armature.tech/leaderboards/auth.md)
- [Email providers](https://armature.tech/leaderboards/mail) (https://armature.tech/leaderboards/mail.md)
- [Product analytics](https://armature.tech/leaderboards/product-analytics) (https://armature.tech/leaderboards/product-analytics.md)
- [Databases](https://armature.tech/leaderboards/databases) (https://armature.tech/leaderboards/databases.md)
- [File storage](https://armature.tech/leaderboards/storage) (https://armature.tech/leaderboards/storage.md)
- [LLM evals & observability](https://armature.tech/leaderboards/evals) (https://armature.tech/leaderboards/evals.md)
- [Serverless functions](https://armature.tech/leaderboards/serverless) (https://armature.tech/leaderboards/serverless.md)
- [Cloud](https://armature.tech/leaderboards/cloud) (https://armature.tech/leaderboards/cloud.md)
- [AI gateway](https://armature.tech/leaderboards/ai-gateway) (https://armature.tech/leaderboards/ai-gateway.md)
- [Bot protection](https://armature.tech/leaderboards/bot-protection) (https://armature.tech/leaderboards/bot-protection.md)
- [Search](https://armature.tech/leaderboards/search) (https://armature.tech/leaderboards/search.md)
- [Agent frameworks](https://armature.tech/leaderboards/agent-frameworks) (https://armature.tech/leaderboards/agent-frameworks.md)
- [Performance in CI](https://armature.tech/leaderboards/perf-ci) (https://armature.tech/leaderboards/perf-ci.md)