Rasa Voice

by Rasa

Open-source conversational AI framework with voice channel integration.

TL;DR

Open-source conversational AI framework with voice channel integration.

Best for enterprises self-hosting a conversational AI stack with on-prem governance needs. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows, Cloud

What it is

Rasa is a long-running open-source conversational AI framework with NLU, dialog policies, and now LLM-powered CALM stories. Voice deployments wrap Rasa with Twilio Media Streams, Genesys, or Audiocodes connectors plus an ASR/TTS pair. Rasa is the default choice when buyers need self-hosted control and a transparent training pipeline.

Best for: Enterprises self-hosting a conversational AI stack with on-prem governance needs.
Watch out for: Voice channel typically requires custom telephony adapters or third-party connectors.

Install / use

pip install rasa

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

Rasa Voice vs Whipscribe

FeatureRasa VoiceWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsLinux, macOS, Windows, CloudWeb, API, MCP

Alternatives to Rasa Voice

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 22.3k

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.