How accurate is Reson8?

Reson8 transcribes the 1,000 public Pipecat clips at 2.10% word error rate and the eight licensed Ocular recordings at 2.93%. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.

How fast is Reson8 in a live conversation?

First text arrives after 2.40s at the median, and the transcript is final 235ms after the speaker stops. Both are measured on the same 206 streamed turns as every other model, and the page shows P90 and P95 as well, which is what a caller meets on a bad turn.

How was Reson8 measured?

Every model runs the same two datasets under the same conditions: 1,000 public clips from Pipecat's STT benchmark dataset for accuracy at scale, and eight licensed conversation recordings from Ocular for real speech. Latency comes from 206 streamed turns, using each provider's own supported finalization contract. Reson8 returned usable text for 1,000 of the public clips.

Bench

Book a demo

Reson8

Every model

Accuracy vs. speed

Lower and further left is better · Nemotron 3.5 Transcribe doesn't support streaming, so it is not shown

Best quadrantBest picks

Final-text delay P50 (ms)

Overall WER (%)

Reson8 is 2nd of 19 on the Ocular Dataset and 14th of 16 on time to first text.

2.38% Overall WER (3rd) · 2.10% Pipecat WER (6th) · 2.93% Ocular WER (2nd) · 2.40s First text (14th) · 235ms Final text (13th)Likely range, 95% confidence: Pipecat WER 1.86 to 2.35%, Ocular WER 2.29 to 3.68%Published price $0.12 per hour of streamed audio. Reson8's real-time rate as of Oct 28, 2026. Source, checked Oct 8, 2026.

Last updated Sep 16, 2026Methodology by Dileep Chagam

Reson8 against every other model

Lower is better on every measure. Hover a column for that model's full numbers.

Glossary: WER, TTFT, TTFS, P50

WER · Word error rate: Share of words the model got wrong: replaced, missing or added. Lower is better.
Pipecat Dataset: 1,000 short public clips from Pipecat's STT benchmark dataset.
Ocular Dataset: 8 recordings from 4 real phone conversations, licensed from Ocular.
Likely range · 95% range: Where the model's true score probably falls, given how much audio was tested. Overlapping ranges are too close to call.
TTFT · Time to first text: How long after the audio starts streaming until the first words appear.
TTFS · Final-text delay: How long after the caller stops until the full transcript arrives. A voice agent waits for this before it replies.
P50 / P90 / P95 · Typical, slow and slowest turns: Half of turns are faster than P50. Only 1 in 10 is slower than P90, and 1 in 20 slower than P95.

Where Reson8 struggled

On real calls, dropped words are its biggest source of error. On clean clips, wrong words lead. Our guide explains how word error rate is measured.

46%

of its errors on the Ocular calls are words it left out.

Median across all 19 models: 49%

Mix of errors

Real calls (Ocular Dataset)

Clean clips (Pipecat Dataset)

TTFT and TTFS at P50, P90 and P95

Timed on the same 206 streamed Ocular turns as every other model. P90 and P95 show what a caller meets on a slow turn.

TTFS, final text

How long after the caller stops until the full transcript arrives. A voice agent waits for this before it replies.

20ms50ms100ms200ms500ms1s2s

Typical, P50: 235ms; 13th fastest of 18
Slow, P90: 357ms; 12th fastest of 18
Slowest, P95: 398ms; 11th fastest of 18

TTFT, first text

How long after the audio starts streaming until the first words appear.

200ms500ms1s2s5s10s20s

Typical, P50: 2.40s; 14th fastest of 16
Slow, P90: 7.97s; Slowest of 16
Slowest, P95: 10.20s; Slowest of 16

Every other model's typical turn, on the same axis.

1,000 Pipecat clips · 8 Ocular recordings · 201 turns timed · 0 failed requests

Reson8 FAQ

Where does Reson8 place in the benchmark?

Reson8 places highest on the Ocular Dataset, 2nd of 19 at 2.93%. Its weakest placing is time to first text, 14th of 16 at 2.40s.

Reson8 places highest on the Ocular Dataset, 2nd of 19 at 2.93%. Its weakest placing is time to first text, 14th of 16 at 2.40s.
Reson8 transcribes the 1,000 public Pipecat clips at 2.10% word error rate and the eight licensed Ocular recordings at 2.93%. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
First text arrives after 2.40s at the median, and the transcript is final 235ms after the speaker stops. Both are measured on the same 206 streamed turns as every other model, and the page shows P90 and P95 as well, which is what a caller meets on a bad turn.
Every model runs the same two datasets under the same conditions: 1,000 public clips from Pipecat's STT benchmark dataset for accuracy at scale, and eight licensed conversation recordings from Ocular for real speech. Latency comes from 206 streamed turns, using each provider's own supported finalization contract. Reson8 returned usable text for 1,000 of the public clips.

Building on Reson8? Test your agent the same way.

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

Book a demo Start free