HF Text Generation Inference (TGI)
Don’t want to install HF Text Generation Inference? 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.
Production inference server — runs audio-multimodal LLMs.
Upstream is archived. HF Text Generation Inference (TGI)’s repository has been set read-only by its owner, so there are no further releases, fixes, or security patches. The last commit landed 2026-03-21. It can still be cloned and run, and forks may be maintained elsewhere. See the repository.
Best for self-hosting Qwen2-Audio / SeamlessM4T / Phi-Audio over HTTP. Pricing: free.
What it is
HF's production-grade inference server. HFOIL license — check before commercial deployment.
Watch out for: ASR-specific paths newer than text-only ones.
Install / use
What people actually do with HF Text Generation Inference (TGI)-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.
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 99 |
| HIPAA eligible | No |
Links
HF Text Generation Inference (TGI) vs Whipscribe
| Feature | HF Text Generation Inference (TGI) | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | $6–$24 one-time packs (credits never expire) · first 20 minutes free |
| Speaker identification | No | Named in the summary, key quotes and chapters |
| Word timestamps | Yes | Yes |
| Streaming | No | No |
| Languages | 99 | 99 |
| Platforms | Linux, Docker | Web, API, MCP |
Alternatives to HF Text Generation Inference (TGI)
Frequently asked about HF Text Generation Inference (TGI)
Is HF Text Generation Inference (TGI) free?
Yes. HF Text Generation Inference (TGI) is free and open source.
Does HF Text Generation Inference (TGI) work on Mac, Windows and Linux?
HF Text Generation Inference (TGI) runs on Linux and Docker. It is not listed for other platforms; check the vendor for anything beyond Linux and Docker.
How do I install HF Text Generation Inference (TGI)?
Clone and run it from source: `git clone https://github.com/huggingface/text-generation-inference`. Expect to install its dependencies yourself — the README has the exact steps per OS.
How many languages does HF Text Generation Inference (TGI) support?
HF Text Generation Inference (TGI) lists 99 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.
Does HF Text Generation Inference (TGI) identify different speakers?
No. HF Text Generation Inference (TGI) 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 HF Text Generation Inference (TGI) give word-level timestamps?
Yes — HF Text Generation Inference (TGI) produces timing per word, which is what subtitle cues and clip boundaries need.
Can HF Text Generation Inference (TGI) transcribe live audio?
No — HF Text Generation Inference (TGI) works on finished files, not a live stream.
Is HF Text Generation Inference (TGI) HIPAA compliant?
HF Text Generation Inference (TGI) 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 HF Text Generation Inference (TGI)?
ASR-specific paths newer than text-only ones.
Who is HF Text Generation Inference (TGI) best for?
Self-hosting Qwen2-Audio / SeamlessM4T / Phi-Audio over HTTP.
Does HF Text Generation Inference (TGI) run offline?
HF Text Generation Inference (TGI) runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Can I use HF Text Generation Inference (TGI) in the browser?
No — HF Text Generation Inference (TGI) is a Linux and Docker application, not a web app. You install it rather than sign in to it.
Where is the HF Text Generation Inference (TGI) source code?
On GitHub at github.com/huggingface/text-generation-inference. It is maintained by Hugging Face.
What kind of tool is HF Text Generation Inference (TGI)?
In this directory HF Text Generation Inference (TGI) is filed under framework, accelerator, server as a open-source tool.
What are the alternatives to HF Text Generation Inference (TGI)?
There is a side-by-side page at /tools/text-generation-inference-alternatives comparing HF Text Generation Inference (TGI) 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
Running HF Text Generation Inference (TGI) yourself? Send the same file here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step
Explore
All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing
Have the recording already?
Skip the setup and send the file or the link: see MP3 to text for long recordings, transcribing a podcast episode and an SRT subtitle file from any recording.
Looking at paid options?
Before you choose a transcription tool or service: see an honest roundup of the best transcription services, cheap transcription services and the real cost per hour and our transcription service with prices and turnaround.