Text-to-speech

IndexTTS-2 requirements, license & speed

By bilibili (IndexTeam) · released 2025-06-18

Hugging Face ↗ GitHub ↗ Compare

Commercial useConditional
Min memoryNot stated
Runs on CPUUnknown
StreamingUnknown

Key facts

License
bilibili Model Use License Agreement source
Commercial use
Conditional source
Commercial use: contact indexspeech@bilibili.com
Parameters
Unknown
Minimum memory
Not stated by source
Runs on CPU
Unknown
Streaming
Unknown
Voice cloning
Yes source
Single reference clip
Languages
zh, en source
IndexTTS-2.5 adds ja, es, ar
Released
2025-06-18 source
Hugging Face repo creation date (proxy for release date)
Gated on HF
No

Measured speed & memory

Benchmark pending. We haven't measured IndexTTS-2 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.