Research Interactive explainer

How speech-to-speech models become believable voice agents.

Speech agents feel magical only when several technical loops line up: audio tokens, conversational context, turn-taking, streaming generation, interruption handling, and latency budgets. This page lets you poke each layer instead of reading a static essay.

full-duplex voice loop~240 ms target
Listen
VAD + encoder
Think
LLM + audio tokens
Speak
codec decode
Adapt
prosody + timing
~240 msfull-duplex voice loop target
5pipeline stages to click through
5latency sources to tune
4turn states to step through
4quiz questions at the end
01 Model pipeline

Speech-to-speech is not just ASR + LLM + TTS.

The easy mental model is a three-box cascade. Modern systems are more nuanced: they preserve timing, speaker cues, prosody, uncertainty, and interruption state while streaming partial output.

02 Sesame CSM

CSM generates speech as conversational audio tokens.

Sesame’s open CSM is a contextual speech generation model. It is not a general multimodal assistant by itself; it is the voice generator that turns text plus conversational audio context into natural speech.

Click a CSM component

CSM uses a Llama-style backbone and a smaller audio decoder. It predicts Mimi/RVQ audio codes, then the codec decodes those codes into waveform audio.

03 Latency lab

Voice UX is won or lost in hundreds of milliseconds.

The user does not care where delay came from. Capture, VAD, network, inference, codec decoding, and playback buffering all add up. Drag the sliders to feel why “fast model” is not enough.

End-to-end response budget

Approximate time from “user stops or yields” to first audible assistant audio. Lower is better, but too-aggressive turn detection causes interruptions.

0 ms
estimated time to first audio
Calculating…
04 Turn taking

The hard part is deciding when not to talk.

Humans use breaths, prosody, gaze, hesitation, and semantics to coordinate turns. Voice agents fake this with signal processing, prediction, and carefully tuned state machines.

Interactive turn-state machine

Step through the runtime loop. The best systems can barge in, back off, fill pauses, and repair misunderstandings without exposing machinery.

05 Architectures

Three ways to build a spoken assistant.

Each design has a different failure mode. Most production systems are hybrids because reliability, latency, and expressivity pull in different directions.

PatternHow it worksStrengthFailure mode
Cascade
ASR → LLM → TTS
Transcribe speech to text, generate text, synthesize voice.Debuggable, controllable, easy to integrate tools and safety.Often loses prosody, timing, emotion, and interruption nuance.
End-to-end S2S
audio in → audio out
Model consumes audio features/tokens and emits audio tokens directly.Can preserve paralinguistic information and reduce handoff friction.Harder to inspect; may hallucinate what it heard or be weaker at tool use.
Contextual TTS
LLM text → expressive voice
Separate reasoning model writes text; a speech model uses context audio/text to speak it naturally.Great control plus strong voice presence when context is rich.Requires orchestration: context windows, speaker state, and timing policy.
06 Why Sesame feels good

“Insane UX” is a stack, not one model trick.

The demos that feel alive combine model capability with product discipline. The model supplies expressive speech; the runtime makes it conversational.

Voice presence

Voice carries confidence, uncertainty, warmth, and timing. Sesame explicitly frames the goal as “voice presence,” not just clean audio.

  • consistent persona
  • emotionally appropriate prosody
  • style adapts to context

Contextual generation

CSM can condition on prior text and audio segments, so a line can be spoken as a continuation of the conversation instead of a standalone clip.

  • speaker history
  • previous rhythm
  • content-aware emphasis

Low-latency streaming

Great agents start speaking before the whole answer is done. Audio tokens are decoded in chunks and scheduled into a smooth playback buffer.

  • first-audio target
  • jitter buffer
  • incremental decoding

Turn prediction

VAD alone is not enough. A model needs to know if a silence means “done,” “thinking,” or “about to continue.”

  • pause thresholds
  • semantic endpointing
  • barge-in policy

Repair behavior

Mishearing is inevitable. The UX win is a short, specific repair instead of a generic “I did not understand.”

  • repeat only when needed
  • quote what was heard
  • ask narrow clarifiers

Agent speech

The assistant should not read every internal thought. It needs spoken phrasing: shorter clauses, fewer lists, and more timing-aware delivery.

  • speech-first copy
  • backchannels
  • natural stop points
07 Check your model

Quick comprehension test.

If these feel easy, you understand the real engineering split: model architecture, runtime orchestration, and product UX.