Prerecorded, realtime, and turn-level transcription on EU-hosted infrastructure.
3 integrated models · Official documentation ↗
Batch endpoint of Reson8, a Netherlands-hosted speech-to-text provider, for uploaded files in ten European languages including Frisian, with optional diarization of up to eight speakers, word timestamps and phrase biasing toward domain terms.
Reson8's WebSocket streaming transcription for live audio in the same ten European languages, returning interim and final results with flush control, per-transcript speaker labels and custom-model biasing, processed on Reson8's own GPUs in the Netherlands.
Turn-aware streaming endpoint from Reson8 for voice agents, emitting turn-start, turn-end-candidate and turn-end events with adjustable eager and final probability thresholds instead of a continuous transcript stream.