gpt-realtime
Ranked 4 of 6 voice AI models by recommenders
Recommended for low-latency speech-to-speech and strong capabilities. Caveat: critics say it is expensive, with weaker full-duplex overlap.
Recommended for low-latency speech-to-speech and strong capabilities. Caveat: critics say it is expensive, with weaker full-duplex overlap.
12 people gave an opinion
- recommend it
- 6
- criticize it
- 6
- approval share
- 50%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 1 recommender for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Very low latency streaming
“very similar results with low latency streaming which gives you this feeling of an assistant that is there in the room with you”
Comment from 8 Jul 2026 in “GPT‑Live” “very low latency speech-to-speech but quite expensive”
Comment from 3 Mar 2026 in “Show HN: I built a sub-500ms latency voice agent from scratch” Capable, robust model
“Love the models, speed, and capabilities.”
Comment from 24 Feb 2026 in “GPT-Realtime-1.5 Released” “gpt is super good, seemingly more robust”
Comment from 9 May 2026 in “OpenAI's WebRTC Problem”
What people warn about
Each mark is one comment
Expensive for voice use
“very low latency speech-to-speech but quite expensive”
Comment from 3 Mar 2026 in “Show HN: I built a sub-500ms latency voice agent from scratch” “ended up spending near $1”
Comment from 31 Jul 2026 in “Advancing the price-performance frontier with GPT‑5.6”
Other voice AI models people recommend
The four most recommended other voice AI models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GPT-Live | 72 | 48 | 60% | 4 | — | — |
| Gemini Live | 50 | 23 | 68% | 9 | — | Approved |
| Nvidia PersonaPlex 7B | 14 | 8 | 64% | 4 | — | — |
| gpt-realtimeThis page | 6 | 6 | 50% | 4 | — | — |
| Sesame voice demo | 5 | 1 | 83% | 3 | — | — |
What people said
All 13 comments that mention it, newest first. Each links to the original comment.
“It would be completely absurd to have to use the recommended gpt-realtime-2.1-mini model for TTS instead”
“which gpt-realtime-2.5 didn't”
“it responds too soon with filler at awkward times”
“ended up spending near $1”
“very similar results with low latency streaming which gives you this feeling of an assistant that is there in the room with you”
“the multi modal stuff has resulted in a lot of debugging with weird events”
“almost there, but not quite good enough for our use case”
“gpt is super good, seemingly more robust”
“they do not seem to be quite the same level of overlapping realistic full duplex”
“very low latency speech-to-speech but quite expensive”
“Love the models, speed, and capabilities.”
“Initial feel from a few calls is that it seems to perform better with alphanumeric inputs”
“I've had pretty bad results from gpt-realtime”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.