Skip to content

Rumble-2-Flash is now open weights, Apache 2.0.

Read the announcement

Glossary

Short definitions of terms used throughout the API and this documentation.

Term Description
Access token A short-lived bearer token obtained by exchanging an API key at POST /v1/auth/token. Used for client-side applications to avoid exposing the API key directly.
API key A secret token used to authenticate requests to the Reson8 API. Scoped to a single client.
Barge-in The user interrupting a speaking voice agent. On the turns endpoint, a turn_start while the agent speaks signals it. See Turns.
Base model The transcription model a request uses, such as Rumble-2, chosen with the model parameter. Custom models extend it rather than replace it. See Models.
Code switching Changing language during a session. Picked up between utterances with auto-detection or a language list, not within one. See Code switching.
Confidence score The model’s probability for a recognized word, in (0, 1]. Available when include_confidence is enabled.
Custom model A collection of phrases that biases transcription toward domain-specific vocabulary. See Custom Models.
Filler words Hesitation sounds such as “um” and “uh”. Whether they appear in transcripts is controlled by filler_mode. See Filler Words.
Final result A stable transcription that will not change as more audio is received. Indicated by is_final: true.
Flush A request to force the server to finalize any buffered audio and return a transcript immediately. The server responds with a flush confirmation.
Interim result A partial transcription that may be revised as more audio is processed. Useful for live feedback during streaming.
Pattern A regex-style description of a short structured token, such as an order code or licence plate, to recover in transcription. See Patterns.
PCM Pulse-code modulation - a raw, uncompressed audio encoding. The pcm_s16le format (16-bit signed, little-endian) is supported when encoding is set explicitly.
Phrases Terms that bias transcription toward your vocabulary, passed per request via the phrases parameter or collected in a custom model.
Segment A per-speaker piece of a diarized prerecorded response, with its own text and speaker ID. See Diarization.
Self-hosting Running Reson8 on your own Kubernetes cluster and GPUs, so audio never leaves your network. Available on request. See Self-Hosting.
Session An active WebSocket connection during which audio is streamed and transcriptions are returned.
Speaker ID An integer label for a speaker within a session, assigned in the order speakers are first heard. See Diarization.
Turn One speaker’s stretch of speech in a conversation, opened by turn_start and closed by turn_end. See Turns.
Turn end candidate An early signal that a turn is ending, carrying the transcript so far. Each candidate replaces the previous one; turn_end confirms the last. See Turns.
Utterance A continuous stretch of speech, ended by a pause. In realtime each final transcript covers one utterance; in turns, one turn.