Listen to Coda.
Then call one.
Two engineering demos on the same model. A full customer-support call read by one voice end to end, and an A/B of four voices on a single companion script. Audio is real.
One model. Two demos.
The first demo is consistency: same voice across five moments of a real support call. The second is range: same prompt, different voices, to hear what Coda's catalog actually sounds like before you pick. Both end with an option to talk to a live Rime expert.
Five moments, one Wawona.
First touch
“Hi! Thanks so much for calling. I see you're having trouble with your order. Let me pull that up real quick and we'll figure it out together.”
Reading the problem
“Okay, I'm looking at your order right now. Looks like the shipment got delayed at the warehouse. Honestly, that shouldn't have happened. I'm really sorry about that.”
Offering a way out
“Here's what I can do for you. I can either get a new order out today on overnight shipping, no extra charge, or I can process a full refund right now. Whichever works better for you.”
Catching the wrinkle
“Oh, hold on, I'm seeing one more thing here. Looks like the tracking had an older address on it. Can you confirm your current shipping address so I get this right?”
Wrapping it up
“Got it. So we'll have that out today, you should see it tomorrow morning. Anything else I can help with? Thanks so much for your patience, really appreciate it.”
Same script, four voices.
Vespera
01“Hi, I'm so glad you called. So, this is the part where we just get to know each other a little. There's no script, no right answer. I'm just gonna ask you a few things, and we'll see where it goes. Sound good?”
Arcade
02“Same script, different read. Bright, curious, present.”
Celeste
03“Okay, so most apps want to know your height and where you went to school. I'm more interested in something else. What's been on your mind this week?”
Marlu
04“Same script, different read. Easy, intimate, conversational.”
Vespera
05“Hm. The way you said that. It sounded like it actually matters to you. You know, I think the people who pay attention to things like that are usually the ones who care about the right stuff.”
Ask the Rime expert. Live.
Same voice, same model. Ask about models, latency, normalization, custom voices, the on-prem container — anything you'd want to know for an eval.
Three paths.
Hosted
Hit the Rime cloud TTS endpoint with your API key. Set modelId: "coda" and you get everything you heard above. Lowest setup cost.
On-prem
We package the Coda container and ship it. TTFB around 140 ms on an H100 or RTX 6000. Same API surface, your network.
Custom voice
Brand-owned voice trained in the Coda family, ~3 to 4 weeks end to end if it's on the roadmap.