Pocket TTS
Hacker ApprovedShares rank 3 of 18 text-to-speech models by recommenders
Small, fast local text-to-speech model that runs on CPU and clones voices from short clips. Critics note skipped words and a prohibited-use clause.
Small, fast local text-to-speech model that runs on CPU and clones voices from short clips. Critics note skipped words and a prohibited-use clause.
57 people gave an opinion
- recommend it
- 41
- criticize it
- 16
- approval share
- 72%
Recommended in 8 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 41 people recommend itNeeds 10 or more, met.
- 2.6 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, 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
Fast on modest hardware
“Pocket is small and fast and has good enough voice cloning.”
Comment from 24 Jan 2026 in “Ask HN: What's the current best local/open speech-to-speech setup?” “This works great! even on a phone with 2GB of RAM finally”
Comment from 8 Jul 2026 in “Show HN: PocketTTS-raven – fast local in-browser TTS with voice cloning” “amazing quality and also crazy fast on both gpu and cpu”
Comment from 24 Jan 2026 in “The State of Modern AI Text to Speech Systems for Screen Reader Users” - Comment from 23 Sep 2026 in “Gemini 3.8 text-to-speech”
- Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
- Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
Good voice cloning
“I've tried the voice clinking and it works great. I added a 9s clip and it captured the speaker pretty well.”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “It is also very easy to make new voices from small sample files with pocket-tts.”
Comment from 7 Jul 2026 in “Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro” “pocket-tts is much better especially when you rip a good voice”
Comment from 7 Jul 2026 in “Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro” - Comment from 24 Jan 2026 in “Ask HN: What's the current best local/open speech-to-speech setup?”
- Comment from 8 Jul 2026 in “Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro”
- Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
- Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
Natural, high-quality speech
“The audio feels very natural and it's fairly good at handling complext text to speech tasks.”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “Pocket TTS has more natural intonation and voice cloning.”
Comment from 8 Jul 2026 in “Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro” “amazing quality and also crazy fast on both gpu and cpu”
Comment from 24 Jan 2026 in “The State of Modern AI Text to Speech Systems for Screen Reader Users” - Comment from 23 Jan 2026 in “Qwen3-TTS Family Is Now Open Sourced: Voice Design, Clone, and Generation”
- Comment from 24 Jan 2026 in “Ask HN: What's the current best local/open speech-to-speech setup?”
Runs on laptops and phones
“It's really pushing the envelope of what is possible to run locally on everyday devices.”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “This works great! even on a phone with 2GB of RAM finally”
Comment from 8 Jul 2026 in “Show HN: PocketTTS-raven – fast local in-browser TTS with voice cloning” “runs well on my macbook, much better than Samantha!”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
What people warn about
Each mark is one comment
Skips or reorders words
“skips "we had nothing before us" and doesn't speak the final "that some of its noisiest"”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “but the problem is Javert skips over parts of sentences!”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “it skipped whole parts and then also moved words around”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” - Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice”
MIT license conflicts with prohibited use
“It says MIT license but then readme has a separate section on prohibited use”
Comment from 15 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” “the README containing a "Prohibited Use" section definitely creates a conflicting statement”
Comment from 16 Jan 2026 in “Pocket TTS: A high quality TTS that gives your CPU a voice” Latency and realtime limits
“it didn't solve the latency issues fully due to leading silence and artifacts generation”
Comment from 8 Jul 2026 in “Show HN: PocketTTS-raven – fast local in-browser TTS with voice cloning” “Not super productive for realtime work.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
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 TTSThis page | 41 | 16 | 72% | 8 | — | Approved |
| Qwen3-TTS | 41 | 13 | 76% | 7 | — | Approved |
| Kitten TTS | 33 | 7 | 83% | 4 | — | Approved |
What people said
40 of the 72 comments that mention it, newest first. Each links to the original comment.
“It's stupid fast and the voice quality is decent.”
“This works great! even on a phone with 2GB of RAM finally”
“this looks (and sounds) like a pretty cool thing!”
“The goal was to preserve the intended PocketTTS quality while making it fast enough for low-latency interactive scenarios.”
“it didn't solve the latency issues fully due to leading silence and artifacts generation”
“Pocket TTS has more natural intonation and voice cloning.”
“It is also very easy to make new voices from small sample files with pocket-tts.”
“i can get the onnx int8 version to reach 5x”
“actually performs (both speed and quality-wise) better than the ONNX version”
“pocket-tts is much better especially when you rip a good voice”
“Not super productive for realtime work.”
“randomly outputs something pretty weird sounding mixed in with like 90% good outputs”
“the amazing 100M-parameter Pocket-TTS [1] model”
“People underestimate just how much more immediately usable something becomes when you can simply get something by doing”
“amazing quality and also crazy fast on both gpu and cpu”
“amazing speech quality (English only)”
“Pocket is small and fast and has good enough voice cloning.”
“pocket tts is probably my second choice for similar reasons”
“excellent in both speed and quality (English only)”
“this one is tiny, so it's not the sharpest tool in the shed”
“similar to chatterbox as far as realism at half the speed and no gpu needed”
“It's impressive but it's a shame that it's 2026 and despite remarkably lifelike speech”
“it generates at 2x speed on CPu”
“The voice cloning also worked much better than expected!”
“apart from voice cloning nothing really new”
“This is impressive but in a sample I tried, it switched language on the second paragraph.”
“It's really pushing the envelope of what is possible to run locally on everyday devices.”
“It's pretty good. And for once, a software-engineering-ly high-quality codebase, too!”
“it skipped "we had everything before us," in my test”
“I've tried the voice clinking and it works great. I added a 9s clip and it captured the speaker pretty well.”
“runs well on my macbook, much better than Samantha!”
“skips "we had nothing before us" and doesn't speak the final "that some of its noisiest"”
“The audio feels very natural and it's fairly good at handling complext text to speech tasks.”
“it skipped whole parts and then also moved words around”
“Being able to voice clone with PocketTTS seems major”
“but the problem is Javert skips over parts of sentences!”
“the README containing a "Prohibited Use" section definitely creates a conflicting statement”
“something that runs so efficiently on cpu”
“It says MIT license but then readme has a separate section on prohibited use”
“Just made it an MCP server so claude can tell me when it's done with something”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.