All tasks / Voice & audio / Text to speech
Best local AI for text to speech
Open-weights models and tools that run entirely on your own hardware, ranked from public benchmarks. Local tools are rated by the best open model they run.
ATop ranked: Fish Audio Drama 3 (Preview) (Fish Audio), 1,244 on Artificial Analysis Speech Arena: Text to Speech (provider voices).15 options listed · data verified 19 Oct 2026
Ranked list
| Tier | Name | Approach | Runs | Rated by | Price | Skill |
|---|---|---|---|---|---|---|
| A |  Fish Audio Drama 3 (Preview)Fish Audio | Models | Local | 1,244 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~48 GB VRAM | — |
| B |  Breeze TTS 2BreezeBlue | Models | Local | 1,222 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~12 GB VRAM | — |
| C |  Step-Audio-EditXStepFun | Models | Local | 1,100 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~8 GB VRAM | — |
| C |  Voxtral TTS (4B, 2603)Mistral AI | Models | Local | 1,089 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~10 GB VRAM | — |
| C |  Kokoro-82M v1.0hexgrad | Models | Local | 1,064 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~1 GB VRAM | — |
| C |  Magpie-Multilingual 357M (Feb 2026)NVIDIA | Models | Local | 1,064 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~1 GB VRAM | — |
| C |  Maya1Maya Research | Models | Local | 1,046 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~8 GB VRAM | — |
| C |  Higgs TTS 3 (4B)Boson AI | Models | Local | 1,042 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~12 GB VRAM | — |
| C |  VibeVoice-1.5BMicrosoft | Models | Local | 957 on Artificial Analysis Speech Arena: Text to Speech (provider voices) | ~8 GB VRAM | — |
| C |  VoiceboxJamie Pine (open source) | Apps | Local | via Kokoro-82M v1.0 | Free | beginner |
| C | sherpa-onnx k2-fsa (Next-gen Kaldi) | Local servers & APIs | Local | via Kokoro-82M v1.0 | Free | advanced |
| C |  Kokoro-FastAPIremsky (open source) | Local servers & APIs | Local | via Kokoro-82M v1.0 | Free | intermediate |
| C |  Speachesspeaches-ai (open source) | Local servers & APIs | Local | via Kokoro-82M v1.0 | Free | advanced |
| C |  TTS WebUIrsxdalv (open source) | Local servers & APIs | Local | via Kokoro-82M v1.0 | Free | intermediate |
| C |  NVIDIA NeMo SpeechNVIDIA | Local servers & APIs | Local | via Magpie-Multilingual 357M (Feb 2026) | Free | advanced |
Tiers come only from public benchmarks (Artificial Analysis Speech Arena: Text to Speech (provider voices)); tools without a result of their own inherit the tier of the best model they offer. How we rank.