SintelSES / Models
Find the model for your task.
Compare installed speech models by language, sample rate and capabilities.
Installed engines
Model and capability comparison.
Only installed models and their reported languages are shown. Available voices and capabilities depend on the selected model and package.
| Model | Task | Languages | Sample rate | Capabilities |
|---|---|---|---|---|
| Emira | TTS | 48 kHz | Turkish speech synthesis with decoder streaming. | |
| Sonik | TTS | 44.1 kHz | Sonik speech synthesis with text-chunk streaming. | |
| Duru | TTS | 24 kHz | Local speech synthesis using an installed model. | |
| Ahen | TTS | 48 kHz | Local speech synthesis using an installed model. | |
| Piko | TTS | 24 kHz | Speech synthesis with autoregressive streaming. Voices and languages follow the installed packages. | |
| Duyum | ASR | 16 kHz | File transcription and revisable text previews. | |
| Nemo | ASR | 16 kHz | Native streaming transcription for live audio. | |
| Seda | ASR | 16 kHz | Native streaming transcription for live audio. |
Let’s discuss your call flow.
Let’s review your existing telephony and customer systems and prepare a demo around your use case.