Text-to-speech
XTTS v2 requirements, license & speed
By Coqui · released 2023-10-31
Commercial useNo
Min memoryNot stated
Runs on CPUUnknown
StreamingYes
Key facts
- License
- Coqui Public Model License (CPML) source
- Commercial use
- No sourceCPML is a non-commercial license
- Parameters
- Unknown
- Minimum memory
- Not stated by source
- Runs on CPU
- Unknown
- Streaming
- Yes sourceREADME: XTTS can stream with <200 ms latency
- Voice cloning
- Yes source6-second reference clip, cross-language
- Languages
- 17 languages source
- Released
- 2023-10-31 sourceHugging 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: 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.