Text-to-speech

XTTS v2 requirements, license & speed

By Coqui · released 2023-10-31

Hugging Face ↗ GitHub ↗ Compare

Commercial useNo
Min memoryNot stated
Runs on CPUUnknown
StreamingYes

Key facts

License
Coqui Public Model License (CPML) source
Commercial use
No source
CPML is a non-commercial license
Parameters
Unknown
Minimum memory
Not stated by source
Runs on CPU
Unknown
Streaming
Yes source
README: XTTS can stream with <200 ms latency
Voice cloning
Yes source
6-second reference clip, cross-language
Languages
17 languages source
Released
2023-10-31 source
Hugging Face repo creation date (proxy for release date)
Gated on HF
No

Measured speed & memory

Benchmark pending. We haven't measured XTTS v2 yet. Planned targets: CPU (8 vCPU), Apple Silicon Mac, RTX-class consumer GPU and a rented cloud GPU. Get notified.

Similar TTS models

Spotted an error? Report it. Every fact links to the model card or repo it came from.

New open speech models, tested. Weekly.

One email when a model ships: license, memory, and real speed on a Mac, a gaming GPU and a cloud GPU.