TTS Voices
Streamerly offers a library of text-to-speech voices in two engine types, covering a wide range of languages and styles.
Engine Types
| Engine | Quality | Notes |
|---|---|---|
| Standard | Good | Lightweight synthesis, fast generation, broad voice selection |
| Neural | High | AI-enhanced synthesis with more natural-sounding output |
Both engine types are available across the supported languages. You can mix engines freely across your triggers.
Languages
The voice library covers 30+ languages and locales. Each voice is tagged with a BCP 47 language code (e.g., en-US, ja-JP, de-DE) so you can filter to match your audience.
Choosing a Voice
- Want the most natural sound? → Pick a Neural voice
- Want a lightweight default? → Pick a Standard voice
- Streaming in multiple languages? → Add voices for each language to your trigger's voice list
You can use any combination of voices across your triggers — you're not locked into one.
See Also
- Voice Management — Select and configure voices
- TTS in Alerts — Set up TTS in your triggers