---
title: "Real-time factor (RTF) and RTFx"
description: "RTF is processing time over audio length, so lower is faster; RTFx is the inverse, so higher is faster. How to read 174x realtime, with Phonon-2's figures."
canonical: "https://www.fermionresearch.com/glossary/real-time-factor/"
source: "Fermion Research"
---

Glossary/facts checked 13 November 2026

# Real-time factor (RTF) and RTFx

Two ways of writing the same speed number, and the measurement details that decide whether two of them can be compared.

[Phonon-2.5 benchmarks and downloads](https://www.fermionresearch.com/models/phonon-2-5/)Open weights on Hugging Face.

## The short answer

Real-time factor (RTF) is the time a system takes to process audio divided by the length of that audio: lower is faster, and anything below 1 keeps up with live speech. RTFx, the inverse real-time factor, is audio length divided by processing time: higher is faster.

"174x realtime" is an RTFx of 174, which is an RTF of about 0.0057. It means one hour of audio is transcribed in about 21 seconds (3,600 / 174 = 20.7).

## RTF, RTFx and latency

The first two are throughput measures and convert into each other. Latency is a different thing.

| Measure | Formula | Better when | For a 174x realtime system | Answers |
| --- | --- | --- | --- | --- |
| Real-time factor (RTF) | processing time / audio duration | Lower | 0.0057 | Can it keep up with live audio? |
| RTFx (inverse RTF, "x realtime") | audio duration / processing time | Higher | 174 | How much audio per second of compute? |
| Time per audio hour | 3,600 s / RTFx | Lower | about 21 s | How long does a batch job take? |
| Latency | time from end of speech to final text | Lower | not implied by RTFx | How long does a user wait? |

## Reading published figures: Phonon-2 as an example

The figures below are Phonon-2's published numbers, converted. There are no published speed figures for Phonon-2.5. Note the last row: a batched figure is total throughput across many files at once, not the speed of one stream.

| Phonon-2, published | x realtime (RTFx) | RTF | One hour of audio |
| --- | --- | --- | --- |
| Apple Neural Engine via Core ML, M5 MacBook Air | 606 | 0.0017 | about 6 s |
| GPU of a base M5 MacBook Air via MLX | 174 | 0.0057 | about 21 s |
| Eight AMD Zen 5 cores, CPU engine | 143 | 0.0070 | about 25 s |
| Google Axion (Arm CPU) | 52 | 0.0192 | about 69 s |
| CPU of an M5 MacBook Air | 40 | 0.0250 | 90 s |
| NVIDIA H100, batched | 6,680 | 0.00015 | about 0.5 s of compute per hour, across a batch |

## When two speed numbers are comparable

- Same hardware: a GPU number and a laptop CPU number differ by orders of magnitude for the same model.
- Same batching: one stream at a time and a large batch measure different things.
- Same scope: some figures time only the model, others include loading the model, decoding the audio file and writing output.
- Same audio: long files and short clips amortise overheads differently.

The Open ASR Leaderboard reports RTFx for every model it runs, measured by the maintainers on one hardware type (the repository names a single H200 for official runs). Leaderboard RTFx values compare models with each other on that machine; they do not predict speed on a laptop.

## Questions

## Related

- [On-device speech recognition](https://www.fermionresearch.com/glossary/on-device-speech-recognition/)
- [Phonon-2](https://www.fermionresearch.com/models/phonon-2/)
- [Phonon-2 on Core ML](https://www.fermionresearch.com/models/phonon-2/core-ml/)
- [The Open ASR Leaderboard](https://www.fermionresearch.com/glossary/open-asr-leaderboard/)
- [Speech-to-text API cost](https://www.fermionresearch.com/speech/speech-to-text-api-cost/)

## Sources and method

- Speed figures: Phonon-2's published figures (/models/phonon-2/ and /research/phonon-2/), M5 MacBook Air, AMD Zen 5, Google Axion and H100 hosts as stated.
- Open ASR Leaderboard: github.com/huggingface/open_asr_leaderboard README, read 2026-11-13.
- Srivastav et al., Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation, arXiv 2510.06961 (first version 2025-10-08), read 2026-11-13.

Canonical: https://www.fermionresearch.com/glossary/real-time-factor/

Source: [https://www.fermionresearch.com/glossary/real-time-factor/](https://www.fermionresearch.com/glossary/real-time-factor/)
