Azure Realtime vs Deepslate Opal

Compare
Azure RealtimeMicrosoft
Wins 11 of 11
Reliability (Pass³)
37.1%
Latency P50
1.86s
Cost per Minute (USD)
$0.080
Deepslate OpalDeepslate
Wins 0 of 11
Reliability (Pass³)
12.9%
Latency P50
2.46s
Cost per Minute (USD)
$0.112

Azure Realtime is ahead of Deepslate Opal on all 11 metrics.

Last updated Methodology by Dileep Chagam

Who is better at what

Azure RealtimeDeepslate Opal
  • ELO Rating1017847
  • Hearing6760
  • Turn Taking6946
  • Speaking7771
  • Task Handling7854
  • Reliability (Pass³)37.1%12.9%
  • Pass Rate (score ≥ 80)54.8%31.4%
  • Task Completion Rate25.7%12.4%
  • Dead-Air Rate (≥ 10 s)6.2%16.2%
  • Latency P501.86s2.46s
  • Cost per Minute (USD)$0.080$0.112

Results by call

Right every time, on booking and Healthcare calls

Banking callsHealthcare calls
  1. 31%
    43%
    Azure Realtime
  2. 9%
    17%
    Deepslate Opal

Azure Realtime vs Deepslate Opal FAQ

  • Azure Realtime is more reliable, by 24.3 points. Azure Realtime handled 26 of 70 real callers well on all three runs, and Deepslate Opal 9. A caller only counts when every run of the call scored 80 or more.

  • For a voice agent, Azure Realtime, since it handles more real callers well on every run. Azure Realtime is ahead of Deepslate Opal on all 11 metrics.

  • Azure Realtime, by 13.3 points higher. Azure Realtime fully resolved 25.7% of calls and Deepslate Opal 12.4%. A call counts only when every step the caller needed was done.

  • Yes. Azure Realtime starts replying 0.60s sooner at the median. Azure Realtime takes 1.86s at the median and 2.10s at p90; Deepslate Opal takes 2.46s and 3.16s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

  • Azure Realtime, by 10.0 points. The agent went quiet for 10 seconds or more on 6.2% of Azure Realtime calls and 16.2% of Deepslate Opal calls.

  • Azure Realtime is $0.032 cheaper a minute. Azure Realtime costs $0.080 a minute of call and Deepslate Opal $0.112, at each vendor's published rates.

  • Cekura ran both as the whole agent with the same prompt, tools and phone connection. Both took the same 70 recorded real human callers on live calls, three times each. Each call is graded on 25 skills across Hearing, Turn Taking, Task Handling and Speaking, and passes at a score of 80 out of 100.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.