Models

LLMs and speech run at providers. The turn-taking models run locally, on your CPU, inside the engine. This catalog (schema/models.json) lists every model Cuelo uses or has evaluated, with its license, size and cost.

cuelo models                     # integrated models
cuelo models --all               # include ones still being evaluated
cuelo models --role turn         # vad, turn, text_turn, barge, agent_backchannel, duplex, component
cuelo models info turn-1-mini
cuelo models pull --all          # download every integrated and experimental model (sha256-verified)
cuelo models pull maai-turn

Weights download on first use into $CUELO_MODELS (default ~/.cache/cuelo/models), pinned to a revision and checked by sha256.

Status:

• integrated: a Cuelo controller uses it.
• experimental: runs, but its controller isn't a default.
• evaluating: being tested.
• evaluated: tested and not integrated.
• unsupported: can't run locally, or its license blocks it.

Roles:

• vad: speech presence.
• turn: end of turn from audio.
• text_turn: end of turn from the transcript.
• barge: interruption versus user backchannel.
• agent_backchannel: when the agent says "mhm".
• duplex: models that hear both sides.
• component: shared parts, such as encoders.

IntegratedCopy Anchor Link

silero-vadCopy Anchor Link

Speech presence, 20 ms frames. Feeds every controller; not end-of-turn on its own.

smart-turn-v3Copy Anchor Link

Semantic end of turn from audio: judges at each pause whether the speaker sounds done.

turn-1-miniCopy Anchor Link

Streaming end of turn from audio, a score every 20 ms. Fastest endpointing in our tests.

backchannel-detectorCopy Anchor Link

While the agent talks: user backchannel ("yeah") vs real interruption.

maai-turnCopy Anchor Link

Voice Activity Projection from user + agent audio: end of turn and real interruptions vs backchannels.

Holds all 3 real mid-sentence cuts; complete turns end 380-980 ms after speech; interrupts caught 80-160 ms after the user starts, backchannels let through. The non-Kyoto English VAP weights are CC-BY-NC-ND (not used). It also ends the turn in 0.6 s pauses between complete sentences of a longer story; pair it with maai-backchannel so the agent says "mhm" there.

maai-backchannelCopy Anchor Link

When the agent should say "mhm": VAP-BC timing from both audio channels.

Kit monologue at p>=0.5: 4/4 pauses hit, 1 extra trigger (after the turn ended). Vendored MaAI matches upstream within 5e-4.

maai-mimi-encoderCopy Anchor Link

Streaming Mimi audio encoder (ONNX) shared by the MaAI models.

ExperimentalCopy Anchor Link

backchannel-cueCopy Anchor Link

Picks which reaction the agent says (61 forms: mhm, oh no, nice, ...) from the live transcript.

Phrase choice is good; its own gate fires too often (10/10 mid-sentence at the card's 0.09). Use it for wording, with a timing model deciding when.

EvaluatingCopy Anchor Link

anyreach-semantic-turnCopy Anchor Link

Text-only: start speaking / keep listening / start listening / keep speaking.

License-clean text detector; weights (473 MB) not yet downloaded here.

EvaluatedCopy Anchor Link

dualturn-endpointingCopy Anchor Link

Dual-channel audio end of turn with future speech-activity signals (Mimi features).

Fast on complete turns (240-280 ms) but also ends turns on real mid-sentence cuts (460-680 ms); no barge/backchannel head. Not integrated: turn-1-mini / maai-turn are more selective.

dualturn-0.5bCopy Anchor Link

Dual-channel floor control: end of turn, hold, backchannel, yield.

Not evaluated end to end: 6.6 GB weights; heavier than the controllers above.

UnsupportedCopy Anchor Link

tygerCopy Anchor Link

Two-stream controller: listen / hold / speak / backchannel, interruption and endpoint scores.

Can't keep up on CPU. Plausible on GPU/MPS later; OpenMDW-1.1 allows commercial use with notices.

easy-turnCopy Anchor Link

Audio + linguistic turn state: complete, incomplete, backchannel, wait.

Not a streaming controller, trained mostly on Mandarin, no agent channel.

livekit-turn-detectorCopy Anchor Link

End of turn from the STT transcript.

License forbids standalone use or use with other frameworks; also deprecated by LiveKit.

Adding a modelCopy Anchor Link

To integrate a new turn-taking model, add a catalog entry and a controller. See Add a turn-taking model.