vsref
Chatterbox logo

Chatterbox Review

OSS

Production-minded open TTS from a commercial voice company - MIT license, built-in watermarking, and a fast Turbo variant, with Resemble's paid API as the scale-up path.

Among the 46 text-to-speech tools we track, Chatterbox has the 18th-widest language coverage.

See pricing

Facts verified Jul 20, 2026Website →

What we know about Chatterbox

Chatterbox sits in the text-to-speech apis category, where it is production-minded open TTS from a commercial voice company - MIT license, built-in watermarking, and a fast Turbo variant, with Resemble's paid API as the scale-up path. We keep this Chatterbox profile grounded in primary sources, each fact dated to when we last confirmed it.

Chatterbox does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Chatterbox quote, it is the fastest way for us to close that gap.

On capabilities, Chatterbox covers instant voice cloning, emotion / style controls, and self-host / on-prem option. Each of those is verified against Chatterbox's own docs or dashboard, not marketing copy.

Among the 46 text-to-speech tools in our matrix, Chatterbox leads with the 18th-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 11 verified facts for Chatterbox today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Chatterbox fact sheet below.

Reviewed by vsref Editorialfacts verified Jul 20, 2026Methodology →

Fact sheet

Capabilities
Capabilities facts
Instant voice cloning✓ YesJul 20
Languages supported23 languagesJul 20
Emotion / style controls✓ YesJul 20
Compliance & trust
Compliance & trust facts
Self-host / on-prem option✓ YesJul 20
Model weights licenseMITJul 20
Build experience
Build experience facts
Official SDKsPyTorch (pip `chatterbox-tts`)Jul 20
Commercial
Commercial facts
Model size (parameters)500M (Chatterbox / Multilingual V3), 350M (Chatterbox-Turbo)Jul 20
Hardware to self-hostCUDA GPU, CPU, or Apple MPS supportedJul 20
Hosted API availableYesJul 20
Project maintenance statusactiveJul 20
GitHub stars25,600 starsJul 20

Considering a switch? Best Chatterbox alternatives →

STT in this stack

Text-to-speech is half of a voice pipeline: the other half is the speech-to-text that listens. Compare transcription engines on accuracy, streaming latency, and per-minute price: Deepgram, AssemblyAI, GPT-4o Transcribe, or the full speech-to-text comparison →

Voice agents in this stack

The engine is one layer: a voice agent speaks through its text-to-speech engine, but orchestration, telephony, and turn-taking come from the agent platform. Compare the platforms builders pair Chatterbox with: Pipecat, OpenAI Realtime API, Twilio ConversationRelay, or the full voice-agent comparison →

Distribute it

Most Chatterbox voiceover ends up in short-form video, and publishing that video across TikTok, YouTube, and Instagram is a scheduling problem with real per-channel pricing. Compare the schedulers creators actually run: Buffer, Postiz, Mixpost, or the social media scheduling platforms compared →

Avatar video in this stack

A cloned or bring-your-own Chatterbox voice does not have to stay audio-only: AI avatar video platforms lip-sync it onto a talking avatar for finished video. Compare the platforms: HeyGen, Synthesia, Hedra, or the full avatar-video comparison →