Text-to-speech

Miso TTS 8B requirements, license & speed

By Miso Labs · released 2026-05-21 · ~8.2B parameters

Commercial useYes
Min memory24 GB VRAM recommended (bf16); ~20 GB RAM on CPU (slow)
Runs on CPUUnknown
StreamingUnknown

Key facts

License
Modified MIT source
Commercial use
Yes source
Products with >50M MAU or >$10M monthly revenue must display 'Miso Labs'
Parameters
~8.2B source
Minimum memory
24 GB VRAM recommended (bf16); ~20 GB RAM on CPU (slow) source
Runs on CPU
Unknown
Streaming
Unknown
Voice cloning
Yes source
Conditions on prior audio context
Languages
en source
Released
2026-05-21 source
Hugging Face repo creation date (proxy for release date)
Gated on HF
No

Measured speed & memory

Benchmark pending. We haven't measured Miso TTS 8B 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.

New open speech models: will they run on your hardware?

One email a week: new open TTS/STT models, license gotchas, and what we measured on CPUs, Macs, Pis and consumer GPUs.