VoicEra

A complete voice AI building block with telephony integration, featuring real-time speech-to-text, text-to-speech, and LLM-powered conversational agents.

Could not verifysource: GitHubhomepagePythonApache-2.0commit 2960b2818576

Python, Apache-2.0 licensed. The project labels itself: ai calling, conversational ai, inbound calls, language ai, local llm, no code, on prem voice agent platform and open source.

Argusic could not get VoicEra running. An Argusic agent installed it in 25 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Python venv with all dependencies installed; 448 tests pass using mocks for FerretDB, MinIO, and Redis; the Docker application stack and frontend could not be launched due to missing Docker and Node.js 18 being too old for Next.js respectively.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 50 of 100 (the mean of this project's run scores).

At a glance

verdict
Could not verify
Argusic Score
50 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
318
forks
85
open issues
25
watchers
2
size
35 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing VoicEra, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Catalog updated bulbul:v2 to bulbul:v3 but 3 tests still referenced v22 minutes
  • test_sarvam_voice_options_split_by_model asserted anushka voice not in v3 catalog2 minutes
  • Missing pytest-asyncio plugin caused 24 async test failures1 minute
  • Node.js 18.19.1 too old for Next.js (needs >=20.9.0); frontend cannot build
  • Docker not available; cannot start full application stack or run docker-dependent tests
Install time
25 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
pytest on apps/api/tests: 129 passed, 1 skipped; apps/providers/tests: 68 passed, 1 skipped; apps/runtime/tests: 41 passed; model-server/tests: 210 passed, 94 skipped, 1 failed (pre-existing env doc gap). total 448 passed, 1 failed, 96 skipped.
Model tokens used
196,387
Exact commit tested
2960b2818576
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

4. Docker unavailable — no fix possible; `test_grpc_facade.py` skips.
**Result** — 448 tests pass, 1 pre-existing env-doc failure, 94 model-server skips (voice pipeline …
tokens used
196,387
Now let me summarize the full evaluation:
**Install**: Python venv created, all pip dependencies installed. Docker not available, so compose-…
**Fixable errors**:
1. Missing `pytest-asyncio` (async tests couldn't run) — installed it.
2. Catalog test referenced `bulbul:v2` but the catalog only has `bulbul:v3` — fixed in `test_config…
3. A test asserting `anushka` in bulbul:v3 voices — `anushka` removed from catalog; adjusted assert…
4. Docker unavailable — no fix possible; `test_grpc_facade.py` skips.
**Result** — 448 tests pass, 1 pre-existing env-doc failure, 94 model-server skips (voice pipeline …

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 25 minutes.
  • Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • An agent with no time limit did not get it running.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run50.000.03
Argusic Runner1/3Did not run50.000.07

Topics (from GitHub)

ai-callingconversational-aiinbound-callslanguage-ailocal-llmno-codeon-prem-voice-agent-platformopen-sourceopen-source-voice-aioutbound-callspipecatpythonself-hostedtelephonyvoice-aivoice-ai-agentsvoice-ai-platform

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/VoicEra.svg)](https://argusic.com/subject/voicera)

Questions

Does VoicEra run?
Argusic could not verify that VoicEra runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test VoicEra?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2960b2818576. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test VoicEra?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does VoicEra take to install?
25 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does VoicEra need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing VoicEra?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for VoicEra?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion