How fast is live stream translation?

In our July 2026 measurements, streaming speech recognition (Deepgram nova-3) produced interim text with no measurable processing lag behind speech, locked final transcripts a median of 0.79 seconds after a phrase ended, and machine translation added a median of 241 ms. Typical end-to-end latency for a locked translated subtitle was about 1 second, with 90th-percentile outliers around 2.5 seconds.

What is the fastest live stream translation tool?

As of July 2026, no other live stream translation vendor has published measured latency figures, so a like-for-like ranking is not possible. StreamTranslate's measured pipeline delivered translated subtitles in roughly 1 second (median) end-to-end. Local OBS plugins such as LocalVocal depend heavily on the streamer's hardware and Whisper model choice and publish no figures.

How was this benchmark measured?

Real speech audio was streamed to the speech-recognition service in 100 ms chunks at real-time pace over a websocket. Latency was computed as wall-clock arrival time of each transcript minus the position of the corresponding audio's end in the stream. Translation latency was the median of timed API calls on ten streamer-typical phrases (English to Spanish). Methodology and limitations are published in full on this page.

Does local (on-PC) translation have lower latency than cloud?

Not necessarily. Local plugins avoid network round-trips but run Whisper-class models on the streamer's own hardware while it is already encoding video, so latency varies from near-real-time on a strong GPU to multi-second on CPU. No local plugin has published measured figures. Cloud pipelines add network hops but run on dedicated inference hardware.

Home · Blog · Latency Benchmark 2026

Live Stream Translation Latency Benchmark 2026

Measured numbers, full methodology, raw data, and the limitations — because as of publication, nobody in this space has published a real latency benchmark. So we did.

Published July 21, 2026 · Measurements taken July 21, 2026 · By the StreamTranslate engineering team

Quick Answer

In our measurements, streaming speech recognition produced on-screen interim text with no measurable processing lag behind speech, locked final transcripts a median of 0.79 s after a phrase ended, and machine translation added a median of 241 ms. Typical end-to-end time for a locked, translated subtitle: ≈1 second, with 90th-percentile outliers around 2.5 s.

Why this benchmark exists

Every tool in the live captioning and translation space makes a latency claim — "real-time," "minimal lag," "under X seconds" — and none of them, including us until today, published measurements behind the claim. This page is our attempt to fix that: real numbers, the exact method used to get them, and an open invitation to every other vendor to publish theirs the same way.

Results

Stage 1 — Streaming speech-to-text (Deepgram nova-3, our production model)

Metric	n	Median	p90	What it means for a viewer
Interim results (text appearing as you speak)	25	≈0 ms processing lag	≈0 ms	Live text keeps pace with speech; the delay a viewer perceives comes from phrase chunking, not processing.
Final results (locked transcript after a phrase ends)	8	790 ms	2,065 ms	The corrected, final version of a caption lands well under a second after you stop talking, in the typical case.

Stage 2 — Machine translation (English → Spanish, production racer endpoint)

Provider	n	Median	p90	Notes
Google translation endpoint (tier-1 racer in our provider race)	10 phrases	241 ms	427 ms	Measured from a neutral US cloud network. Our production servers race multiple providers and take the first response, so production translation latency is at or below this figure.

End-to-end (what a viewer experiences)

Path	Composition	Typical (median)	p90
Live text path (interim + translate + deliver)	≈0 ms + 241 ms + delivery	≈0.3 s behind speech	≈0.5 s
Locked subtitle path (final + translate + deliver)	790 ms + 241 ms + delivery	≈1.0–1.1 s after phrase end	≈2.5 s

Delivery (WebSocket push from server to the OBS overlay) was not independently measured in this run; it is typically tens of milliseconds and is included above as an unmeasured minor term. We label it as such rather than inventing a number.

How this compares to other tools

Honestly: it can't be compared head-to-head yet, because no other vendor in this space has published measured latency figures. Here is the state of public claims as of July 2026:

Tool	Architecture	Published latency data	Public claim
StreamTranslate	Cloud STT + provider-race translation, browser-source overlay	Yes — this page	Under 2 s (supported by measurement above)
LocalVocal (OBS plugin)	Local Whisper-class model on the streamer's own PC; CTranslate2/M2M100 for translation	None published	"Minimal lag" — varies with GPU/CPU and model size chosen; the machine is simultaneously encoding video
Maestra	Cloud transcription suite with live captioning tools	None published	"Real-time"
Akkadu	Cloud live captions	None published	"Real-time"
LiveTL	Human volunteer translators in chat	N/A	Human-speed (typically several seconds, quality can exceed machines)

If you are one of these vendors and you publish measured figures with comparable methodology, we will link them from this page. Standing offer.

Methodology

Speech-to-text: real human speech (28 s of natural talking-head audio, 16 kHz mono PCM) streamed to Deepgram's live websocket API (nova-3, our production model) in 100 ms chunks at exact real-time pace.
Latency definition: for every transcript event, latency = wall-clock arrival time minus the stream-position of the end of the audio that the transcript covers. This is the standard streaming-STT latency measure — it cannot be gamed by buffering.
Translation: ten streamer-typical English phrases ("That was insane, did you see that play?" etc.) translated to Spanish via the same Google endpoint our production race uses; median and p90 of timed calls reported.
Environment: neutral US cloud machine — not our production servers, and not colocated with any provider. Production infrastructure is faster than this, not slower.

Limitations (read these before citing us)

Single speaker, single language pair (EN→ES), one 28-second sample. Final-transcript sample size is small (n=8 phrase finals). We will re-run with more speakers, languages, and longer sessions and update this page.
Competitor tools were not measured — there is no way to measure a local plugin fairly without standardizing hardware, and no cloud competitor publishes an equivalent endpoint methodology. Their rows above reflect their own public claims only.
The p90 final-transcript latency (≈2.1 s STT alone) shows that outlier phrases can exceed our own "under 2 seconds" typical-case claim. We publish that number anyway; a benchmark that hides its worst numbers isn't a benchmark.
Overlay delivery time is estimated, not measured, in this run.

Raw results

Interim STT latencies (ms, n=25): median −3, max +3 — i.e., within measurement noise of zero processing lag. Final STT latencies (ms, n=8): median 790, p90 2,065, max 2,065. Translation EN→ES (ms, n=10): median 241, p90 427. Measurements taken 2026-07-21.

StreamTranslate Engineering

We build real-time live stream translation for Twitch, YouTube, Kick, and TikTok streamers. This benchmark uses our production STT model and translation endpoints, measured from neutral infrastructure.