Open-source TTS models — quick guide

A curated list of popular Text-to-Speech repositories on Hugging Face for self-hosting and experimentation. Sizes and capabilities change—always read each model card.

Related searches & adjacent tasks

Readers often look for best TTS models, free TTS models, best speech recognition models, free speech recognition models, subtitle generation models, or free subtitle generation models. This page focuses on synthesis (TTS); recognition and subtitles usually rely on ASR (e.g. Whisper-class models) plus timing or translation—see the ASR hub link below.

Note: “Free” usually means open weights; commercial use still depends on each license and voice data policy.

More models & hosted API benchmarks

Selected Hugging Face repositories

Click a repo name to open the model card, examples, and license.

openbmb/VoxCPM2

OpenBMB family — efficient speech modeling; good entry if you follow Chinese OSS tooling around CPM.

k2-fsa/OmniVoice

From k2-fsa (speech / streaming ecosystem). High engagement on HF—worth a look if you already use sherpa-onnx–style stacks.

mistralai/Voxtral-4B-TTS-2603

Mistral Voxtral (~4B) — aligns with Mistral licensing and API story; good if you want one vendor for LLM + speech.

hexgrad/Kokoro-82M

Only 82M parameters but consistently top downloads—great for “get audio fast” prototypes and local narration; many community ports (ONNX, MLX, …).

microsoft/VibeVoice-1.5B

Microsoft VibeVoice line—quality-oriented open weights; confirm exact parameter counts on the card.

fishaudio/s2-pro

Fish Audio S2 Pro (large capacity)—naturalness and multi-speaker / multilingual setups; often evaluated with Fish tooling and Spaces.

Disclaimer

Open weights ≠ unlimited commercial use. Check each License and voice-data statement. Cloud API pricing and SLAs are vendor-specific; Artificial Analysis helps compare quality, speed, and USD per 1M characters for hosted TTS.