AI voice integration

Phone numbers for Cartesia — SIP trunk setup with DIDHub

Cartesia Sonic delivers ultra-low-latency TTS for realtime voice agents. Pair with DIDHub for the PSTN side: SIP trunk + 136-country DID inventory + STIR/SHAKEN A-attestation, with regional ingress to keep the latency budget tight.

Why DIDHub for Cartesia

  • Latency-tight regional ingress. Cartesia's Sonic model is built for sub-100ms TTS. The PSTN hop matters — DIDHub regional edges minimize SIP/RTP latency.
  • STIR/SHAKEN A-attestation. US/CA outbound stays under mobile-carrier spam thresholds.
  • Plays nicely with LiveKit / Pipecat / custom stacks. Cartesia is typically wired into a broader agent framework. DIDHub's BYOC SIP works regardless of the framework.
  • Per-DID flat pricing. Predictable economics for Cartesia-based products.

BYOC setup — step by step

  1. Sign up at /signup and provision DIDs.
  2. Generate DIDHub SIP credentials.
  3. Configure your agent framework (LiveKit, Pipecat, custom) with DIDHub as the SIP carrier.
  4. Wire Cartesia Sonic into the TTS leg of your pipeline.
  5. Test end-to-end latency on a real call — STT → LLM → Cartesia → PSTN egress.
Documentation note. Cartesia's BYOC / SIP trunk configuration UI changes occasionally. The steps above reflect the current pattern at time of writing. If a screen has moved, the underlying values (SIP URI, credentials, allowed source IPs) are the same — check Cartesia's docs for the latest UI path.

Caller-ID configuration

Caller-ID configuration depends on which agent framework you've wrapped Cartesia in (LiveKit, Pipecat, etc.). In all cases, the outbound From-header should be a DIDHub-allocated DID.

For US/CA outbound: DIDHub signs every call with STIR/SHAKEN attestation A on DIDHub-allocated and DIDHub-ported numbers. This is the level that mobile carriers (T-Mobile, Verizon, AT&T) treat with baseline trust — calls signed with weaker attestation are increasingly flagged as “Spam Likely” or sent straight to voicemail. See STIR/SHAKEN explained for the full background.

For non-US destinations: present a local DID as Caller-ID for best answer rates. AI agent calling a Madrid customer should present a +34 (Spanish) Caller-ID, not a US number. DIDHub serves 136 countries with dedicated landing pages so you can match Caller-ID to destination.

Latency & regional ingress

Realtime AI voice is brittle to network latency — an extra 100ms of SIP egress can break the natural-conversation feel. DIDHub operates SIP/RTP edges in:

  • NOAM: Ashburn (US-East), San Jose (US-West), Dallas
  • EU: Frankfurt, Amsterdam
  • APAC: Singapore, Tokyo
  • MENA: Dubai

Pick the edge nearest to your Cartesia inference region. Typical sub-50ms regional ingress for the closest pair. If you need a region we don't list, talk to [email protected] — we add edges in response to customer demand.

FAQ

Why Cartesia for voice agents?

Cartesia Sonic offers some of the lowest-latency TTS in the market — especially valuable for realtime conversational agents where every 100ms matters.

Does DIDHub do anything Cartesia-specific?

No — DIDHub is the carrier; Cartesia is the TTS. They compose via your agent framework.

How tight can end-to-end latency get?

Sub-1s STT + LLM + TTS + PSTN hop is achievable with regional Cartesia + regional DIDHub + a fast LLM.

Can Cartesia voice be used commercially?

Per Cartesia's TOS. DIDHub is just the telephony — voice IP and licensing are between you and Cartesia.

Provision your first Cartesia DID

Sign up at /signup, pick a country / area code, and route the DID to your Cartesia BYOC SIP trunk. $1.99/mo for a US number, sub-60-second activation on most countries. No commits.

Ready to get a number?

Pick a DID in 130+ countries from $1.99/month. Activates instantly on most numbers.