Text-to-speech
Pocket TTS requirements, license & speed
By Kyutai · released 2025-12-29 · 100M parameters
Commercial useYes
Min memoryNot stated
Runs on CPUYes
StreamingYes
Key facts
- License
- cc-by-4.0 source
- Commercial use
- Yes sourceCC-BY-4.0 per HF metadata (repo gated); bundled voices have their own licenses (kyutai/tts-voices)
- Parameters
- 100M source
- Minimum memory
- Not stated by source
- Runs on CPU
- Yes sourceRuns on CPU using 2 cores; ~6x real-time on MacBook Air M4 (vendor figure)
- Streaming
- Yes source
- Voice cloning
- Yes source
- Languages
- en, fr, de, pt, it, es, nl source
- Released
- 2025-12-29 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- Yes accept terms on Hugging Face before downloading
Measured speed & memory
Benchmark pending. We haven't measured Pocket TTS 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.