Bert-VITS2

by fishaudio

Don’t want to install Bert-VITS2? Drop the file here.

The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.

VITS2 + BERT prosody TTS — companion to Whisper.

Linux  ·  free

TL;DR

Best for mandarin/Japanese voice agents. Pricing: free.

Category
Open source
License
AGPL-3.0
Stars
★ 8.8k
Last push
2026-08-03
Pricing
free
Platforms
Linux

What it is

Bert-VITS2 reference. AGPL-3.0.

Best for: Mandarin/Japanese voice agents.
Watch out for: TTS only.

Install / use

What people actually do with Bert-VITS2-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Wire it into Amazon S3n8nMake.comGoogle DriveZapierSlack

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported2
HIPAA eligibleNo

Links

GitHub repo ↗

Bert-VITS2 vs Whipscribe

FeatureBert-VITS2Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$6–$24 one-time packs (credits never expire) · first 20 minutes free
Speaker identificationNoNamed in the summary, key quotes and chapters
Word timestampsYesYes
StreamingNoNo
Languages299
PlatformsLinuxWeb, API, MCP

Alternatives to Bert-VITS2

Frequently asked about Bert-VITS2

Is Bert-VITS2 free?

Yes. Bert-VITS2 is free and open source.

Does Bert-VITS2 work on Mac, Windows and Linux?

Bert-VITS2 runs on Linux. It is not listed for other platforms; check the vendor for anything beyond Linux.

How do I install Bert-VITS2?

Clone and run it from source: `git clone https://github.com/fishaudio/Bert-VITS2`. Expect to install its dependencies yourself — the README has the exact steps per OS.

How many languages does Bert-VITS2 support?

Bert-VITS2 lists 2 languages.

Does Bert-VITS2 identify different speakers?

No. Bert-VITS2 does not label speakers; a conversation comes back as one continuous text. If you need speaker labels, that is a separate tool or a different service.

Does Bert-VITS2 give word-level timestamps?

Yes — Bert-VITS2 produces timing per word, which is what subtitle cues and clip boundaries need.

Can Bert-VITS2 transcribe live audio?

No — Bert-VITS2 works on finished files, not a live stream.

Is Bert-VITS2 HIPAA compliant?

Bert-VITS2 does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.

What are the limitations of Bert-VITS2?

TTS only.

Who is Bert-VITS2 best for?

Mandarin/Japanese voice agents.

Does Bert-VITS2 run offline?

Bert-VITS2 runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use Bert-VITS2 in the browser?

No — Bert-VITS2 is a Linux application, not a web app. You install it rather than sign in to it.

Where is the Bert-VITS2 source code?

On GitHub at github.com/fishaudio/Bert-VITS2. It is maintained by fishaudio.

What kind of tool is Bert-VITS2?

In this directory Bert-VITS2 is filed under tts, research as a open-source tool.

What are the alternatives to Bert-VITS2?

There is a side-by-side page at /tools/bert-vits2-alternatives comparing Bert-VITS2 with the closest tools in the same category on price, platform and features.

Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

Transcribe your recordings

Explore

Have the recording already?

Skip the setup and send the file or the link: see MP3 to text for long recordings, a podcast episode as text from its link and an SRT subtitle file from any recording.

Looking at paid options?

Before you choose a transcription tool or service: see how the best transcription services compare, cheap transcription services and the real cost per hour and how our transcription services work.