Vocode (OSS)

by Vocode

Don’t want to install Vocode? 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.

Open-source Python library for building real-time voice-LLM applications.

Linux, macOS, Windows, Cloud  ·  free

TL;DR

Best for python developers building self-hosted voice-LLM apps from primitives. Pricing: free.

Category
Open source
License
MIT
Stars
★ 3.8k
Last push
2024-11-15
Pricing
free
Platforms
Linux, macOS, Windows, Cloud

What it is

Vocode is an MIT-licensed Python library for building real-time voice-LLM apps. It exposes streaming ASR, agent loops with OpenAI/Anthropic, TTS, and transports for phone (Twilio/Vonage) and browser (WebRTC). Vocode also runs a hosted service (vocode.dev) but the OSS core remains a popular base for custom voice agents.

Best for: Python developers building self-hosted voice-LLM apps from primitives.
Watch out for: More plumbing exposed than turnkey Vapi/Retell.

Install / use

pip install vocode

What people actually do with Vocode (OSS)-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 timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

Links

GitHub repo ↗

Vocode (OSS) vs Whipscribe

FeatureVocode (OSS)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$6–$24 one-time packs (credits never expire) · first 20 minutes free
Speaker identification—Named in the summary, key quotes and chapters
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsLinux, macOS, Windows, CloudWeb, API, MCP

Alternatives to Vocode (OSS)

Frequently asked about Vocode (OSS)

Is Vocode (OSS) free?

Yes. Vocode (OSS) is free and open source.

Does Vocode (OSS) work on Mac, Windows and Linux?

Vocode (OSS) runs on Linux, macOS, Windows and Cloud.

How do I install Vocode (OSS)?

With pip: `pip install vocode`. You need Python and, for most audio tools, ffmpeg on your PATH first.

Does Vocode (OSS) identify different speakers?

No. Vocode (OSS) 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 Vocode (OSS) give word-level timestamps?

No — Vocode (OSS) produces segment or sentence timing only, so subtitle cues can land mid-word.

Can Vocode (OSS) transcribe live audio?

No — Vocode (OSS) works on finished files, not a live stream.

Is Vocode (OSS) HIPAA compliant?

Vocode (OSS) 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 Vocode (OSS)?

More plumbing exposed than turnkey Vapi/Retell.

Who is Vocode (OSS) best for?

Python developers building self-hosted voice-LLM apps from primitives.

Does Vocode (OSS) run offline?

Vocode (OSS) runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use Vocode (OSS) in the browser?

No — Vocode (OSS) is a Linux, macOS, Windows and Cloud application, not a web app. You install it rather than sign in to it.

Where is the Vocode (OSS) source code?

On GitHub at github.com/vocodedev/vocode-core.

What kind of tool is Vocode (OSS)?

In this directory Vocode (OSS) is filed under voice middleware, voice agent, developer framework as a open-source tool.

What are the alternatives to Vocode (OSS)?

There is a side-by-side page at /tools/vocode-oss-alternatives comparing Vocode (OSS) with the closest tools in the same category on price, platform and features.

Can I automate Vocode (OSS)-style transcription without running it myself?

Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.

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, transcribing a podcast episode and the SRT file generator.

Comparing tools before you pay?

If you would rather pay a service than run software yourself: see an honest roundup of the best transcription services, affordable transcription priced per hour and how our transcription services work.