Bench · Text to speech · October 2, 2026

Which voice should Holly speak with?

Holly talks back on your own Mac. So we gave 14 voice models the same four lines, in English, Chinese, and both mixed, and kept every clip.

faster than real time for Kokoro v1.1-zh in Python on the GPU, the model Holly speaks Mandarin with
for Qwen3-TTS 1.7B, which can copy a voice in English and Chinese and still keep up with talking
clips to listen to, from models on one MacBook Air

Our two picks

Two kinds of voice model, and the one we'd reach for in each. Your ears get the final say.

Built-in voices

Kokoro

What Holly speaks with today. Tiny and very fast, with a set of fixed voices in English and Mandarin. It switches to a Mandarin voice for Chinese, so mixed sentences change voice.

real time, in Python on the GPU
memory at most, in audio.cpp
82M
parameters

Voice cloning

Qwen3-TTS

Copies a voice from a few seconds of audio, and keeps that one voice through English, Chinese and both mixed. Whisper heard back of what the 1.7B said, as much as any model we can share that also sounds clean. The 0.6B trades a little of that for speed.

real time for 1.7B, for 0.6B
memory at most, 1.7B
Apache
2.0 license, free to ship

The same family also comes with preset speakers (CustomVoice, tested here) that can take tone instructions like "very happy" (not tested yet), and a version that designs a new voice from a written description (VoiceDesign, not tested yet).

Listen and compare

Pick a line and a voice. Models that copy voices heard the same short clip first, so the difference you hear is the model. Suggested order puts our picks first, then the clearest (how much of each line Whisper heard back), then the ones that sounded off when we listened. You can also sort by speed, memory or size. The ones we can't share audio for are always last.

Speed

Seconds of speech made per second of work, typical across all eight clips. Above 1× it can keep up with a conversation. Heard back: how much of the four lines Whisper wrote down correctly from the clearest run.

Python means mlx-audio on the Mac's GPU, except Kokoro (hexgrad's own kokoro package, PyTorch on the GPU, given the same phonemes as audio.cpp; Holly runs Kokoro with onnx on the CPU today) and S1-mini (PyTorch). audio.cpp is a native engine in C++ on the GPU. Peak memory is the most the run used. Load is the time to start and load the model in audio.cpp.

What we learned

How we tested

What this test can't tell you

Thanks

Every voice here is someone's open work. The models we tested, with their makers and licenses:

And the tools that ran them: audio.cpp by ShugoAI (Apache-2.0), mlx-audio (MIT), hexgrad's kokoro (Apache-2.0), and Whisper large v3 by OpenAI (MIT), which listened back to every clip.

Some clips aren't here. Fish Audio S2 Pro, S1-mini and OmniVoice have non-commercial licenses, and Apple's system voices are licensed for personal use, so we show their numbers but not their audio. Pocket TTS is by Kyutai, under CC-BY 4.0.