OpenAI · read on October 27, 2026
OpenAI GPT-4o mini TTS
OpenAI GPT-4o mini TTS is a TTS (text-to-speech) model from OpenAI. No benchmark in this index times it over 30 days, so it has no speed tier. It has no rank: it is neither timed by Coval nor rated by Artificial Analysis.
- Speed tier
- No tier
- P95 / median
- Not timed / Not timed
- Listener Elo
- Not rated
- Price per 1M chars
- $20
Where it ranks
Artificial Analysis does not rate this model for a use case, and it is not among the fastest, so it appears on no use case page.
The tier and the ranks are computed by this site from the benchmarks' figures, not declared by OpenAI.
Measurements and sources
Speko
| Naturalness score | 1,424 |
| Latency, board chart | 518 ms |
| Latency, model page sweep (median) | 691 ms |
| Numbers and dates pronunciation | 0.44 |
Cekura
| Time to first audio, text sent whole | 688 ms |
Details
| Provider | OpenAI |
| Access | Not collected: license not published by the benchmarks |
| Streaming | A benchmark measures its time to first audio |
| Languages tested | Spanish, German, French, Japanese, Chinese, Korean, Filipino, Norwegian, Thai |
| Measured by | Cekura, Speko |
| Official site | developers.openai.com/api/docs/guides/text-to-speech |
Not collected
Nothing below is estimated. Each line says which measure is missing and why.
- Speed (Coval median time to first audio): not measured by Coval (reading of 2026-10-27, 30-day window)
- Speed (Coval P95 time to first audio): not measured by Coval (reading of 2026-10-27, 30-day window)
- Listener rating (Artificial Analysis Speech Arena Elo): not measured by Artificial Analysis (reading of 2026-10-27)
- Price (Artificial Analysis price per 1M characters): not measured by Artificial Analysis (reading of 2026-10-27)
- Access: license not published by Artificial Analysis or Coval, no official weights release found
Sources
- https://benchmarks.cekura.ai/text-to-speech (read on October 27, 2026)
- https://benchmarks.speko.ai/tts/ (read on October 27, 2026)
Values are copied from these pages on the date shown. The match between this model and its benchmark entries is inferred, because a source writes the name differently: Cekura: “GPT-4o mini TTS”. See the methodology.
Compare it with the reference model: Gradium TTS vs OpenAI GPT-4o mini TTS.