The outcome

Deliver useful live captions or voice input without silently losing, duplicating, or misattributing speech.

Step by step

A workflow you can repeat.

  1. 01

    Define supported audio format, sample rate, languages, latency target, session limit, consent signal, and behavior when the connection fails.

  2. 02

    Create a short-lived authorized connection from a trusted backend and stream correctly paced audio without exposing the project API key to clients.

  3. 03

    Distinguish partial from final turns, order events by session metadata, and buffer rendering so revisions do not appear as duplicate speech.

  4. 04

    Test silence, crosstalk, accents, names, network interruption, reconnects, rate limits, and clean termination with timestamped fixtures.

  5. 05

    Monitor latency, error rate, accuracy samples, concurrency, and spend; redact logs and terminate every session when audio or consent ends.

Working standard

What good use looks like.

  • Keep long-lived keys off clients.
  • Separate partial and final turns.
  • Test reconnects with real audio fixtures.

Official references

Check the current product documentation.