Chatterbox TTS

by Resemble AI

Resemble AI's open-source emotion-aware TTS — community-licensed.

TL;DR

Resemble AI's open-source emotion-aware TTS — community-licensed.

Best for self-hosters wanting expressive TTS with emotion control under a permissive license. Pricing: free (MIT).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (MIT)
Platforms
Linux, macOS

What it is

Chatterbox is Resemble AI's open-source TTS contribution — MIT-licensed, designed for expressive emotional output. Voice cloning remains in the commercial Resemble product. Consent posture: synthetic-only in the open model.

Best for: Self-hosters wanting expressive TTS with emotion control under a permissive license.
Watch out for: English-focused; cloning gated to the commercial Resemble product.

Install / use

pip install chatterbox-tts

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

Chatterbox TTS vs Whipscribe

FeatureChatterbox TTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (MIT)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages199
PlatformsLinux, macOSWeb, API, MCP

Alternatives to Chatterbox TTS

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.