Goal
Treat voice as a first-class design surface — not a final demo pass.
End-of-turn (Flux)
Deepgram Flux models use model-integrated end-of-turn detection. In integrations.yml:
asr:
name: deepgram
language_map:
en:
model: flux-general-en
eot_threshold: 0.7
eot_timeout_ms: 5000| Parameter | Effect |
|---|---|
eot_threshold |
Confidence needed to end the turn (higher = wait for clearer completion) |
eot_timeout_ms |
Maximum silence before forcing end-of-turn |
Experiment: Lower eot_timeout_ms if Atlas waits too long after short answers. Raise it if booking references spoken with pauses get cut mid-way.
This tutorial uses Inspector only. Production telephony channels (SIP, CPaaS) reuse the same Skills; audio format negotiation differs by channel.
Spoken formatting
TTS reads characters poorly when you dump HT12345 as a single token. Instruct the skill to speak references character by character:
H T one two three four five
Put that rule in agent.yml persona and in skill bodies that read codes aloud.
Keep sentences short. Ask one clarifying question at a time. Those persona rules reduce barge-in pressure and cut TTS latency perception.
ASR recovery patterns
Speech recognition will mishear amounts, pins, and booking refs. Build recovery into skills:
- Confirm before side effects —
requires_confirmationwith a response that reads the value back - Re-ask on failure — tools return
ok: false; instruct the skill to retry once - Offer alternatives — list bookings instead of forcing the traveler to dictate a reference
- Handoff early — after repeated failures,
@skill.human_handoff
Demo PIN and booking refs in make show-demo-data are chosen to be speakable.
Verbatim vs rephrase
| Mechanism | Use when |
|---|---|
utter: + responses.yml |
Exact compliance / recording / legal wording |
metadata.rephrase: true on a response |
Greeting can vary slightly while staying on-brand |
| Free LLM prose | Normal conversation |
For voice, prefer verbatim for anything a regulator or brand team would quote.
Inspector workflow
make inspect- Enable the microphone
- Watch partial transcripts while speaking
- Compare text and voice behaviour — skills should work in both modes
- If ASR splits a booking ref, try speaking slower or use the typed channel to isolate Skills logic from speech
Talking point
Latency and turn-taking failures are voice-specific. Progressive control and short spoken utterances are the harness — not a bigger prompt.