Sopro TTS
Shares rank 7 of 18 text-to-speech models by recommenders
Small open text-to-speech model with voice cloning, free and easy to run locally; people like its size and speed, but most critics find the audio quality poor and robotic.
Small open text-to-speech model with voice cloning, free and easy to run locally; people like its size and speed, but most critics find the audio quality poor and robotic.
24 people gave an opinion
- recommend it
- 13
- criticize it
- 11
- approval share
- 54%
Recommended in 2 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 13 people recommend itNeeds 10 or more, met.
- 1.1 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Impressive for its small size
“It's impressive given the constraints! Would you consider releasing a more capable version that renders with fewer artifacts”
Comment from 8 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” “It's sounds shitty. But given the small size and speed it's still impressive.”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” Easy to use and run locally
“Very nice to have done this by yourself, locally.”
Comment from 8 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” “Also increadibly easy to use, thanks for this”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” Promising and expected to improve
“Very cool. I'd love a slightly larger version with hopefully improved voice quality.”
Comment from 8 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” “This is very cool! And it'll only get better.”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
What people warn about
Each mark is one comment
Poor, robotic audio quality
“it sounds absolutely horrible, far worse than computer voices sounded fifteen years ago”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” “It sounds absolutely dreadful. Would drive me nuts to listen to for more than a minute.”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” “It's sounds shitty. But given the small size and speed it's still impressive.”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” - Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
- Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
- Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
- Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
Distorted, unstable speech
“It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.”
Comment from 8 Jan 2026 in “Sopro: A 169M parameter real-time TTS model with zero-shot voice cloning” “it's immediately off putting in distortion and mangling of pronunciation”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” Often fails to match voice
“It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.”
Comment from 8 Jan 2026 in “Sopro: A 169M parameter real-time TTS model with zero-shot voice cloning” “the generated audio is not similar at all, it's not even a proper voice”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU” Not state of the art
“It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.”
Comment from 8 Jan 2026 in “Sopro: A 169M parameter real-time TTS model with zero-shot voice cloning” “I wouldn’t say it’s the best, far from that.”
Comment from 9 Jan 2026 in “Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU”
Other text-to-speech models people recommend
The four most recommended other text-to-speech models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| ElevenLabs | 59 | 20 | 75% | 13 | — | Approved |
| Kokoro TTS | 59 | 9 | 87% | 11 | 1 mo3 owners | Approved |
| Pocket TTS | 41 | 16 | 72% | 8 | — | Approved |
| Qwen3-TTS | 41 | 13 | 76% | 7 | — | Approved |
| Sopro TTSThis page | 13 | 11 | 54% | 2 | — | — |
What people said
23 of the 29 comments that mention it, newest first. Each links to the original comment.
“Smaller, faster, more stable”
“It sounds absolutely dreadful. Would drive me nuts to listen to for more than a minute.”
“they all sound extremely robotic and have very bad artifacts”
“I wouldn’t say it’s the best, far from that.”
“I'd be curious to hear why its advocates believe that this is a net win for society.”
“absolutely terrible and completely unusable for any serious application”
“it's immediately off putting in distortion and mangling of pronunciation”
“Sorry but the quality is too bad.”
“This is very cool! And it'll only get better.”
“It's sounds shitty. But given the small size and speed it's still impressive.”
“the generated audio is not similar at all, it's not even a proper voice”
“It sounds more like a warped cassette tape.”
“Also increadibly easy to use, thanks for this”
“I played the sample audio and it was...horrible?”
“some reference voices can lead to bad voice quality. But if it sounds that bad, it's probably not it”
“it sounds absolutely horrible, far worse than computer voices sounded fifteen years ago”
“the cons massively outweigh the pros”
“In this particular case I can only see downsides”
“Very nice to have done this by yourself, locally.”
“It's impressive given the constraints! Would you consider releasing a more capable version that renders with fewer artifacts”
“The cloning and voice affect is great.”
“Very cool. I'd love a slightly larger version with hopefully improved voice quality.”
“It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.