Chatterbox Turbo

Chatterbox Turbo TTS

A faster Chatterbox with sub-200ms latency and inline paralinguistic tags for laughs, coughs, and chuckles.

Ku soo biir 5,000 xaraf xaddid

Wrap qoraalka ku SSML tags si loo hubiyo xakamaynta saxda ah:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Tags qaabka la doortay fahmo — riix si aad u hoos mid ka mid ah qoraalka aad halkaas oo uu ka dhacaa:

Model this akhriyo qoraalka caadiga ah, sidaas inline tags waa la iska indho tiri. For tag-ku salaysan dareenka, u dhaqaaqo si ay u muujiyaan qaabka sida Orpheus ama Bark.

Define custom pronunciations (word = dhawaaqa):

-12 +12
0.5x 2.0x
Bilaash ah oo leh Piper, VITS, MeloTTS
Your audio soo saaro halkan ka muuqan doonaa. Dooro qaab, ku qor qoraalka, oo guji soo saaro.
Dhaqdhaqaaqa ayaa la soo saaray
0:00
Soo dejisa Soo dejisan.srt Xidhiidhku wuxuu dhamaaday 24h
Free tier: isticmaalka shakhsiga ah. Liisan ganacsi laga bilaabo $ 5 / mo
Jecel TTS.ai? Ka warran saaxiibadaa!

About Chatterbox Turbo

Chatterbox Turbo is Resemble AI's 350M-parameter speed-focused upgrade to Chatterbox, reaching up to 6x real-time generation with sub-200-millisecond latency. It keeps the original's voice cloning while adding inline paralinguistic tags — you can drop [laugh], [cough], or [chuckle] directly into your text and have the model perform them. Every generation carries Perth watermarking for provenance tracking, a nod to responsible-AI deployment. The combination of low latency and expressive non-speech sounds makes it well suited to real-time voice agents and interactive characters. Like the original Chatterbox, it is MIT-licensed and English-focused.

Ugu Fiican: Real-time voice agents, expressive speech with natural sounds

Taabo oo kala soo bax Chatterbox Turbo cod

Eeg

Soo-saarayaasha
Resemble AI
Liisan
MIT
Qiyaamaha
standard
Xawaaraha
fast
Duubista Codka
Haa
Afaf
English
Noocyada ugu badan
1000

Chatterbox Turbo cod

Default

English
Caadi Neutral

Chatterbox Turbo Su'aalaha La Weydiiyo

Turbo is a 350M-parameter model that runs at up to 6x real-time with sub-200ms latency, making it suitable for real-time voice agents where the original Chatterbox would be too slow.

They are inline cues like [laugh], [cough], and [chuckle] that you place directly in the text. The model performs the corresponding non-speech sounds, adding natural expressiveness.

Yes. All generated audio includes Perth watermarking, which supports provenance tracking and helps identify the output as AI-generated.
← Codadka oo dhan