Skip to main content
Baseten is a platform for deploying and serving AI models on autoscaling GPU infrastructure. Rime’s text-to-speech engine images run on Baseten as single-container deployments — the engine validates its own license and serves TTS directly, with no separate router.

​
Get started

Ready-to-use deploy configs for Rime’s models live in the rimelabs/rime-baseten-deploy repository. Each model directory contains a Baseten/Truss config.yaml plus a README with full deploy, secrets, and invocation steps.
ModelDirectory
Rime Coda v1 — flagship expressive TTSrime-coda-v1/
Rime Arcana v3 — multilingual expressiverime-arcana-v3/
Rime Arcana v2 (English) — expressiverime-arcana-v2-en/
Rime Mist v3 — low-latency conversationalrime-mist-v3/
To deploy:
  1. Clone the repo and cd into the model directory you want.
  2. Set three secrets on your Baseten workspace — gcp_rime_service_account (pulls Rime’s private engine image), rime_license, and rime_api_key. The per-model README walks through each. Engine images are license-gated; contact help@rime.ai for access.
  3. Push the config with the Truss CLI:
truss push .
  1. Set the autoscaling concurrency target (each replica handles ~10 concurrent requests before a new one is added). See the model README for the exact Management API call.

​
Invoke

Once deployed, send inference requests to your model’s sync endpoint. The Rime API key is baked in via the rime_api_key secret, so callers authenticate to Baseten only: 
import requests

resp = requests.post(
    "https://model-<model-id>.api.baseten.co/environments/production/sync",
    headers={
        "Authorization": f"Api-Key {BASETEN_API_KEY}",
        "Accept": "audio/webm;codecs=opus",   # or audio/pcm, audio/mpeg
    },
    json={
        "text": "Natural-sounding, accurately-pronouncing AI TTS built for high-stakes enterprise conversations.",
        "speaker": "luna",
        "lang": "en",
    },
)
resp.raise_for_status()
with open("output.webm", "wb") as f:
    f.write(resp.content)
For full setup instructions, including secrets and autoscaling, see the rime-baseten-deploy README for your chosen model.