Chatterbox Turbo

Chatterbox Turbo TTS

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

Kulembetsa for 5,000 characters limit

Wrap wanu malemba mu SSML tags kwa kuwongolera moyenera:

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

Tags chosankhidwa chitsanzo amamvetsa - dinani kuti aphe mmodzi m'mawu anu pamene chimachitika:

Izi ndi njira yolemba malemba oyera, kotero ma tag ophatikizidwa amasiya kuganiziridwa. Kuti mupange ma tag ogwirizana ndi maganizo, gwiritsani ntchito njira yolemba malemba monga Orpheus kapena Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free ndi Piper, VITS, MeloTTS
Audio yanu yopangidwa idzawonekera pano. Sankhani mtundu, lemba mawu, ndipo dinani Kupanga.
Audio Yapangidwa Mofulumira
0:00
Pangani Audio Pezani.srt Kugwirizana kumatha mu 24h
Free tier: kugwiritsa ntchito kwa munthu. Lisensi yamalonda kuchokera ku $ 5 / mo
Kukonda TTS.ai? udzauza anzanu!

Za 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.

Best kwa: Real-time voice agents, expressive speech with natural sounds

Pezani zonse Chatterbox Turbo maganizo

Pa mphindi

Wopanga
Resemble AI
License
MIT
Mtundu
standard
Kuyenda
fast
Kusintha kwa mawu
Yes
Zilankhulo
English
Max characters
1000

Chatterbox Turbo maganizo

Default

English
Choyambirira Neutral

Chatterbox Turbo TTS — Mafunso Ofala

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.
← Mawu onse