FEATURED VOICES01 / 05
two primitives / one loop
The voice stack, unbundled.
Rem hears each turn. Reverie speaks back. Together, they make your existing voice agent feel like a conversation.
Rem / listen
Hear the intent.
Words appear as they are spoken, with timestamps and turn detection for natural handoffs.
streaming transcriptpreview
“Let’s move the appointment to Thursday afternoon…”
word-level timestampsturn detectionpartial results
one clean connection
From first packet to first word.
A small surface area, observable by default. Drop it into the loop you already have.
the realtime loop
Audio in
WebRTC, SIP, or raw PCM
Rem
Streaming speech recognition
Your agent
Tools, memory, and intent
Reverie
Natural speech out
index.ts
const transcript = await rem.listen(stream, {
model: "rem-2",
language: "en",
punctuate: true
});One SDK, streaming by default. Keep control over the audio path, model choice, and every token of spend.
pricing / one shared pool
Simple credits. Clear runway.
Rem and Reverie draw from one shared monthly pool. Four plans. One credit equals one TTS character or one STT second.
Included
Free
$0 / mo
25K credits
Monthly
Starter
$5 / mo
300K credits
Monthly
Growth
$49 / mo
3.5M credits
Monthly
Scale
$299 / mo
25M credits
1 credit = 1 TTS character1 credit = 1 STT secondhard stop at your credit limit
cost comparison / 4 Sep 2026
What would it cost?
Choose monthly usage to compare estimated annual costs for Reverie TTS or Rem STT. Savings show how much less the Lucid estimate is than each alternative.
100 hrs / mo
Estimated Lucid cost / year
$862
At least $1,157 less / year than the alternatives below (closest: Cartesia). Estimate at 100 hrs / mo using Scale rates; not an extra charge on top of a plan.
Estimated annual cost by provider
Lucid ReverieScale · estimated / year$862Lucid estimate
ElevenLabsFlash / Turbo · estimated / year$3,600$2,738 less with Lucid
CartesiaSonic-3.6 Scale · estimated / year$2,018$1,157 less with Lucid
SarvamBulbul v3 · estimated / year$2,286$1,424 less with LucidYearly totals = monthly hours × 12 × public list rates as of 4 Sep 2026. Lucid uses Scale unit rates ($0.043 / STT hr, $0.718 / TTS hr). Cartesia uses published Scale allotments. TTS character billing uses 1,000 characters ≈ 1 minute.
Fast by default
Low-latency streaming paths, not batch APIs wearing a realtime costume.
One shared pool
Use credits across Rem and Reverie without splitting budgets by product.
No surprise charges
Requests stop when your monthly credits run out. Upgrade or wait for the next reset.
observability / call 042healthy
audio received00:00.000
rem partial00:00.081
agent response00:00.143
reverie first byte00:00.214
conversation health
No dropped frames
production, not a promise
Every millisecond has a receipt.
Voice is a chain of tiny failures. Rem and Reverie give you the timing, the partials, and the controls to see what happened — before your user tells you.
Token-level timing and confidence
Region-aware routing with graceful fallbacks
Usage events you can reconcile to a call
questions worth asking
No fog. Just signal.
Still curious? Talk to an engineer, not a form router.
hello@lucidweights.aiYes. They are intentionally framework-agnostic primitives. Bring the audio transport and orchestration layer you already trust; use our SDKs or the streaming APIs directly.
developer docs