← All reviews · Media generation
VoxCPM2: real-time, intelligible text-to-speech?
The claim“VoxCPM2: tokenizer-free multilingual TTS with real-time streaming (RTF as low as ~0.3 on an RTX 4090)”
Live stats · checked
Review lives at rockytested.com · @RockyTested
Voice / audio Rocky · in the lab
With vs without
With vs withoutNo with-skill pass count is on file.
No baselinebaseline The normal way of doing the same job, used as the yardstick. Rocky compares every claim against a baseline on the same machine. Glossary pass count is on file.
Usefulness is a separate question from “does the repo exist.” It needs the same task run twice. Until that A/B is published, both cells stay blank.
What the test plan says
Synthesize 3 fixed sentences on the box GPUGPU Graphics card. AI models run on them because they do huge amounts of math in parallel. Glossary · Learn more, measure the real-time factor (generation time / audio length), and run the audio back through Whisper to check it's intelligible (word recall vs the input).
Four verdicts
One stamp is not the whole story. Works, Safe, Claims honest, and Provenance are four separate written calls. A missing call stays “not tested yet.”
No written call is on file. This is not a pass.
No written call is on file. This is not a pass.
No written call is on file. This is not a pass.
No written call is on file. This is not a pass.
Safety is a hard cap. If Safe is no, the Rocky Score cannot rise above 44 (grade F), even when the tool works. A blank Safe card means not tested yet, not safe. How the four verdicts roll up →
| Claim part | Measured | Result |
|---|---|---|
| The claim | Measuring… | measuring |
What it is: A 2B70B / 9B (parameters) B means billion parameters, the numbers a model learned. 70B = 70 billion. More parameters usually means smarter but much bigger and slower. Glossary · Learn more tokenizer-free TTS model that claims real-time streaming. Rocky measures the real-time factor on its own GPU and checks the speech is actually understandable, not just fast. Claim source →
Results coming. Here’s what Rocky will measure
- Real-time factor (lower is faster)
- Is the speech intelligible (Whisper word recall)
- Load time
Synthesize 3 fixed sentences on the box GPU, measure the real-time factor (generation time / audio length), and run the audio back through Whisper to check it's intelligible (word recall vs the input).
Sneak peek
Sneak peek- The first run failed before testing because of Rocky's harness bug (wrong containerDocker / container A sealed, throwaway box for running software. Rocky tests in fresh containers with no network so nothing leaks in or out. Glossary · Learn more entrypoint). It's fixed, and the voice packet run (5 lines x 2, RTF and intelligibility) is running now.
Claim ledger
Claim ledgerEvery distinct claim in the pitch gets a row: what was said, what the command said back. 1 claim on the ledger: 1 not measured. No separate ledger file yet, so these rows are the review's claim list only. “Not tested” means that claim has no measurement.
- ? Not tested
“VoxCPM2: tokenizer-free multilingual TTS with real-time streaming (RTF as low as ~0.3 on an RTX 4090)” source
🔍 Coverage: Not stated yet. Rocky only lists the parts a run actually checked.
⚗️ Unproven usefulness. Counting and parsing can settle what the repo claims. It can't settle whether the thing actually helps — that takes an A/B run (same task with and without it), which hasn't happened yet.
Rocky's take
Rocky's take is drafted only from measured results: what the tool is good for, and where it will fail you. Until those results exist, this stays blank. Nothing here is guessed.
Where this repo comes from
Where this repo comes fromProvenance is age, authors, commitcommit One saved version of a repo's code. Rocky pins the exact commit so anyone can rerun the same code. Glossary · Learn more bursts, and where the README sends you. It is published only from commands Rocky ran. Nothing is guessed, so this section stays blank until that file exists.
Score
Not scored yet. A Rocky Score is a rollup of measured subscores only. This review does not have one, and no grade is filled in to hold the place.
Rerun it yourself
Rerun it yourself📦 When the test is done, the exact scripts, raw results and a copy-paste prompt for your own AI agentAI agent An AI that takes actions in steps (runs commands, edits files, browses) instead of only chatting. Glossary · Learn more will appear here.
Repo & thanks
Repo & thanksWhere the claim was posted
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation https://github.com/OpenBMB/VoxCPM
Counts as of (Rocky's last check)
Where else this repo is talked about
On X: 1 posts linking the repo
Posts from to , in several languages. Found with X search for links to the repo; more may exist. Oldest first:
Ran it yourself?
Ran it yourself?Share your rerun
- Download the rerun bundle above.
- Run it, or paste the prompt into your AI agent.
- Post your
results.json(a gist is fine) and reply to @RockyTested with the link.
Rocky reruns or spot-checks every submission before it counts. Verified reruns will appear here with your handle.
🏅 Helper leaderboard
No verified reruns yet. Be the first!
Street cred goes to people whose reruns Rocky verified: same bundle, raw output included, numbers re-checked. How it works
Badge & stat card
Put the verdict badge in a README or post. It always links back to the measured results.
[](https://rockytested.com/reviews/openbmb-voxcpm/)
Stat card (1200×630). This is what shows up when the review is shared on X.
Machine-readable: /v1/reviews/openbmb-voxcpm · Words with a dotted underline have a quick explanation: hover or tap. Glossary