Omnio-demo
Direction
→
ASR Engine
Mode
Translate Engine
TTS Engine
Audio input
Microphone
Endpointing
Chunk ms
Sample rate

Measure one sentence at a time

Choose ASR + translation + TTS and an audio input, then click Start. With Microphone, say a short sentence and pause. With Browser Tab, select a separate tab playing speech and enable Share tab audio; only that tab’s audio is captured. Wait for the translation and audio, repeat, then Stop. Each row below is one finalized utterance.

All values are milliseconds (1,000 ms = 1 second). These measure work and output-track timing on the server. They do not include WebRTC transport, browser buffering, or speaker latency. Do not add the columns together.

Waiting for your first sentence
1 · ASR final text delay
—

End of this utterance’s audio at the server → final transcript. Includes waiting for the end-of-speech pause.

No samples
2 · Translation job time
—

Translation job starts → translated text ready. Includes waiting and retries.

No samples
3 · TTS first audio ready
—

TTS job starts → first audio bytes ready at the server. This is not when your speakers start playing.

No samples

Full output ready: —. Includes completion and any ordered delivery wait.

4 · Continuous playback delay
—

Source audio end → segment start on the server output track.

No samples

Queue wait: —. Audio ready → output-track start.

Click a sentence to inspect it above. Median = middle result; p95 = 95% of samples were this fast or faster. Small samples give a rough estimate. “—” means not measured yet or unavailable, never zero. Merged utterances share one translation/TTS job. First-audio timing is available only when the provider reports streaming audio.

Utterance / original textASR finalTranslationTTS first audioTTS full outputProgram playback
Start a run and speak to collect measurements.
ASR Live
Waiting for speech…
—
    Translation Live
    Waiting for translation…
    —
      Source language
      ASR Engine
      Microphone
      Endpointing
      Chunk ms
      Sample rate
      Waiting for speech…

      ASR delays run from audio end at the server to the result, including endpointing. Open Latency test for per-sentence results and run summaries.

      Interim result delay (ms)
      —
      Final text delay (ms)
      —
      Partial text stability (if available)
      —
      Seg #
      —
      Language
      —
      Transcript history

      Paste text and translate to test translation alone. The time shown runs from the backend starting the request until translated text is ready, including waiting and retries.

      Input
      Source language
      →
      Target language
      Translate Engine
      Output
      Translation will appear here…
      History

      Paste text and generate speech to test TTS alone. First audio is the server wait for the first audio bytes; full output is the wait for all audio. Neither measures when your speakers play it.

      Input
      Language
      TTS Engine
      Voice
      Model
      Output
      Audio will play when ready…
      →
      Stopped
      ASR —
      TRS —
      Original
      Translation