🎙 pack: voice-pack

Build voice agents without TCPA + state-recording-consent landmines.

Using Twilio, Vonage, LiveKit, Deepgram, or ElevenLabs? GreatCTO auto-attaches voice-pack on top of your base archetype and ships TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent geo-routing, EU AI Act Art. 50 synth-voice disclosure, and PII redaction gates from day one.

$ npx great-cto init All packs ↗
Auto-attach signals

Detected by CLI when:

twilio · vonage · livekit · deepgram · elevenlabs · hume · ivr · tts · stt

The pack rides on top of your base archetype (web-service, ai-system, fintech, …) — it doesn't replace it. Auto-injects reviewer agents into the pipeline + opens human gates listed below.

Reviewer agents activated

1 specialist added to the pipeline.

01 · voice-ai-reviewer

TCPA + STIR/SHAKEN + state-recording + EU AI Act Art. 50 + deepfake laws (CA AB-2655, TN ELVIS)

Human gates introduced

1 new gate type on top of gate:plan + gate:ship.

GateOwnerTrigger
gate:voice-complianceregulatory leadafter TM, before senior-dev
Required artefacts before senior-dev claims tasks

7 concrete deliverables.

EVAL suite required

4 golden-set scenarios shipped as templates.

Each EVAL has ≥5 test cases, pass threshold, regression interpretation, cross-refs to TM + gates. Run via your existing test framework.

Regulatory surface covered

10 standards / regulations addressed.

TCPA (47 USC § 227) FCC AI Voice Rule (2024) STIR/SHAKEN 12 state two-party recording laws EU AI Act Art. 50 CA AB 2655 TN ELVIS Act CRTC CASL Ofcom CLI Illinois BIPA voice
Real-world examples

30 companies in this space.

Agora
Real-time voice + video API
publicUS
Twilio
Communications APIs
publicUS
Rev.ai
Speech recognition API
subsidiaryUS
Spitch
Voice biometrics + speech analytics
growthCH
Uniphore
Conversational AI for enterprise
series-eUS
Cresta
AI for contact centers
series-dUS
Synthesia
AI video generation platform
series-dGB
Abridge
Generative AI for clinical conversations
series-cUS
Cognigy
Enterprise conversational AI
series-cDE
Decagon
AI customer-support agents
series-cUS
Deepgram
Speech-to-text API for developers
series-cUS
PolyAI
Customer-led voice assistants for enterprise
series-cGB
Speak
Language-learning voice AI
series-cUS
Suki AI
Voice-enabled assistant for clinicians
series-cUS
ElevenLabs
Most realistic text-to-speech AI
series-bGB
Hume AI
Emotionally intelligent voice AI
series-bUS
Phenix
Real-time audio + video streaming
series-bUS
Replicant
Conversational AI for contact centers
series-bUS
Sierra
Conversational AI for customer experience
series-bUS
Speechmatics
Speech-to-text for 50+ languages
series-bGB
Voiceflow
Conversational AI design platform
series-bCA
DeepScribe
Ambient AI medical scribe
series-aUS
LiveKit
Realtime voice + video infrastructure
series-aUS
Vapi
Voice AI infrastructure for developers
series-aUS
Assort Health
Voice AI for patient + staff coordination
seedUS
Bland AI
Voice agents that work 24/7
seedUS
Bolna
Voice AI for outbound + inbound calls
seedIN
careCycle
Voice AI for Medicare and ACA distributors
seedUS
FutureClinic
Digital medical clinics that are 99% AI, 1% doctor
seedUS
Hamming AI
Voice agent testing + analytics
seedUS

Listed companies operate in this space. Inclusion is based on publicly available product descriptions and does not imply endorsement of or by GreatCTO.

FAQ

Common questions about voice-pack.

When does voice-pack auto-attach?
When the CLI detects these signals in your repo: twilio · vonage · livekit · deepgram · elevenlabs · hume · ivr · tts · stt. Override anytime by editing packs: in PROJECT.md.
What human gates does voice-pack introduce?
gate:voice-compliance (regulatory lead). These layer on top of the standard plan/ship gates.
What if my project doesn't match these signals exactly?
You can manually add the pack name to PROJECT.md or run /migrate to re-run detection with updated rules.
30 seconds

Drop GreatCTO into any repo — voice-pack attaches automatically.

$ npx great-cto init
no signup·runs locally·pay your own API