- Reliability
- 70.7%
- Response time
- 1.66s
- Cost / min
- $0.0798
Azure Realtime is ahead on reliability, success rate, agent responses, data accuracy, calls where the agent went quiet, interruption and response time, and Deepslate Opal on cost.
Last updated Methodology by Dileep Chagam
Our guide covers testing OpenAI Realtime API voice agents.
Scenarios the agent passed on every one of its 3 runs.
Azure Realtime is more reliable, by 12.2 points. Azure Realtime passed 58 of 82 scenarios on all three runs, and Deepslate Opal passed 48. A scenario only counts when every run of it passed.
Azure Realtime is more reliable, by 12.2 points. Azure Realtime passed 58 of 82 scenarios on all three runs, and Deepslate Opal passed 48. A scenario only counts when every run of it passed.
For a voice agent, Azure Realtime, since it gets more scenarios right on every run. Azure Realtime is ahead on reliability, success rate, agent responses, data accuracy, calls where the agent went quiet, interruption and response time, and Deepslate Opal on cost.
Azure Realtime, by 7.6 points. Azure Realtime saved everything exactly right on 86.1% of the calls that save data, and Deepslate Opal on 78.5%. On Booking calls, 94.2% against 88.3%. On Medicare calls, 65.2% against 53.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
Yes. Azure Realtime starts replying 0.65s sooner at the median. Azure Realtime takes 1.66s at the median and 2.22s at p90; Deepslate Opal takes 2.31s and 2.88s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Azure Realtime, by 0.02 on a 0 to 5 scale. Azure Realtime scores 4.96 and Deepslate Opal 4.94 for how well the agent handled being talked over.
Azure Realtime, by 2.0 points. The agent went quiet for 10 seconds or more on 4.1% of Azure Realtime calls and 6.1% of Deepslate Opal calls.
Deepslate Opal is $0.0574 cheaper a minute. Azure Realtime costs $0.0798 a minute of call and Deepslate Opal $0.0224, at each vendor's published rates.
Cekura ran both as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and connection. A simulated caller worked through all 82 scenarios on live calls, three times each, 3,936 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
Cekura runs these simulated calls on your agent and scores every one.