Vocode (OSS)

by Vocode

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

Looking at Vocode (OSS)? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

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

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$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsLinux, macOS, Windows, CloudWeb, API, MCP

Alternatives to Vocode (OSS)

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 24.8k

Whipscribe is a managed faster-whisper + whisperX 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.