Text-to-speech
Supertonic 3 requirements, license & speed
By Supertone · released 2026-04-29 · ~99M parameters
Commercial useYes
Min memoryNot stated
Runs on CPUYes
StreamingUnknown
Key facts
- License
- OpenRAIL-M (weights), MIT (sample code) source
- Commercial use
- Yes sourceOpenRAIL-M allows commercial use with use-based restrictions
- Parameters
- ~99M source
- Minimum memory
- Not stated by source
- Runs on CPU
- Yes sourceDoes not require a GPU
- Streaming
- Unknown
- Voice cloning
- No sourceOpen model uses preset voices; zero-shot cloning is offered in Supertone's paid API
- Languages
- 31 languages source
- Released
- 2026-04-29 sourceREADME news entry
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured Supertonic 3 yet. Planned targets: Raspberry Pi 5, CPU-only x86, Apple Silicon Mac and consumer GPUs. Get notified.
Accuracy
We don't run accuracy evals. For quality and intelligibility, check the Hugging Face Open TTS Leaderboard.
Similar TTS models
Spotted an error? Report it. Every fact links to the model card or repo it came from.