Buying guide · 2027
Best voice AI infrastructure in 2027
Teams building a product that talks do not lose the month on the prompt. They lose it on formats. Twilio sends mulaw at 8 kHz. Deepgram wants PCM at 16 kHz. ElevenLabs returns audio in its own shape. A browser client wants something else. Webhooks from Stripe and GitHub are a second pile of one-off parsers. The application code becomes a switch statement.
HZRelay is the routing layer for that pile. Voice, token streams, and webhooks share a session model and one SDK. You still own the prompt, the tools, and what the product is allowed to do. It is in private preview, so this guide is about whether you need that layer at all, and which logos are on the path versus merely nearby.
Connects to
These are the products this workflow actually touches. A mark in this row is a connection or a channel we set up. It is not a customer logo and it is not a partnership.
Twilio
PSTN audio in. Often mulaw at 8 kHz, which is not what the transcriber wants.
Deepgram
Speech to text. Typically wants PCM at 16 kHz.
ElevenLabs
Speech audio back toward the caller.
OpenAI
Token streams that have to reach more than one listener.
Anthropic
The other model path the routing layer is built to sit in front of.
GitHub
Webhooks, so each provider does not get its own parser.
Stripe
The same webhook problem, from payments rather than git.
Sits beside
These are products teams already pay for, or compare in the same shortlist. We are not claiming a native integration unless the sentence under the logo says so.
Slack
Where the on-call discusses the session. Not the media path.
Sentry
Where the application error lands. Different product from the audio relay.
How the shortlist splits
| Product | Role | Best for | What to know |
|---|---|---|---|
| HZRelay | Mecverse | One session model across voice, tokens, and webhooks | Private preview. You keep the product logic. There is no self-serve price on the product page. |
| Hand-written adapters | Sits beside | A single provider pair you will never swap | Reasonable until the second voice vendor, the second model, or the reconnect bug. |
| FlowTux | Mecverse | Internal tickets, not audio | Do not buy the helpdesk and expect it to transcode mulaw. |
| The model vendor’s own realtime API | Sits beside | Teams who will only ever use one model and one voice stack | Fewer moving parts. You will rewrite it if you add a carrier or a second speech engine. |
The path the logos are actually on
Inbound, the product page names Twilio and Plivo for PSTN, WebRTC and raw WebSocket for browsers, and webhooks such as Stripe and GitHub. Outbound, it names ElevenLabs and Cartesia for speech, Deepgram for transcription, and OpenAI and Anthropic for the model, plus your own app. We have marks here for the ones we can show cleanly. Plivo and Cartesia are named in prose because we are not putting up a broken image. Using the mark means “the relay is built to sit between you and this provider.” It does not mean they certify us, and it does not mean your contract with them changes.
Slack and Sentry are beside the path. They are where humans talk about the session and where the app throws. They do not carry the audio. FlowTux connects to Slack, Sentry, and GitHub for tickets. Do not confuse that GitHub connection with HZRelay’s webhook routing. Same logo, different product, different job.
What you still write
The decision to interrupt, the tool calls, the refusal policy, and the thing you are selling. HZRelay exposes session events you would otherwise scrape out of three dashboards: speech start and end, partial and final transcripts, first token, first audio, a barge-in that flushes the buffer, and an adapter error that names the provider. Latency on the product page is shown as stages on a sample path, from audio received to audio sent. Those sample numbers are an illustration of the stages, not a promise that every call lands on them.
If you will only ever use one carrier and one model, a relay can be unnecessary weight. If you already rewrote the audio callback once because a vendor changed a sample rate, you are the user.
Private preview means a conversation
There is no published monthly price and no self-serve signup. Ask what the preview includes before you put a date on a launch slide. Preview is not general availability with a waiting list caption.
A clinic that wants patients to ask about hours is the WhatsApp assistant. A company that wants candidates to take a first interview is InterviewRoom. Neither should be architected as a HZRelay project unless you are building your own product on top of the voice stack and you mean that.
How to trial it without boiling the stack
One inbound and one outbound. Log one session end to end, including a reconnect and a barge-in. Swap one provider in that diagram only after the first path is dull. If the trial starts with five vendors, you will not know which adapter failed.
Keep the provider invoices in view. The relay does not include Deepgram minutes or Twilio calls. Budget those as you do today.
What changes in 2027
In 2027, assume you will change one provider. The infrastructure worth keeping is the kind that makes that change a configuration, with the session events still named the same way. A proof that only works on the original vendor list has not earned a second year.
Questions
Is HZRelay generally available?
No. It is in private preview. There is no self-serve price.
Does it replace Deepgram, ElevenLabs, or OpenAI?
No. It routes between them and your application. You still pay those providers.
Are those companies partners?
No. The marks identify providers on the path. They are not endorsements and not customers.
Can FlowTux do this?
No. FlowTux is the internal ticket queue for Slack, Sentry, and GitHub.
See HZRelay on a call
Bring the workflow you have today. We will show the product against it and say if it is the wrong fit.
Book a demo