Partner Services
Rime
Deploy Rime text-to-speech services on Cerebrium
Rime Partner Service is available from CLI version 1.39.0 and greater
Cerebrium’s partnership with Rime helps teams deliver text-to-speech (TTS) services with efficient deployment, minimized latency, and region selection for data privacy compliance needs.
Setup
- Create a simple cerebrium app with the CLI:
- Rime services use a simplified TOML configuration with the
[cerebrium.runtime.rime]
section. Create acerebrium.toml
file with the following:
- Run
cerebrium deploy
to deploy the Rime service - the output of which should appear as follows:
- Use the Deployment url from the output to send requests to the Rime service via curl request:
The RIME_API_KEY
is available in the Rime dashboard.
Scaling and Concurrency
Rime services support independent scaling configurations:
- min_replicas: Minimum instances to maintain (0 for scale-to-zero). Recommended: 1.
- max_replicas: Maximum instances during high load.
- replica_concurrency: Concurrent requests per instance. Recommended: 3.
- cooldown: Seconds an instance remains active after last request. Recommended: 120.
- compute: Instance type. Recommended:
AMPERE_A10
.
Adjust these parameters based on traffic patterns and latency requirements.
For further documentation on Rime, see the Rime documentation.