Repository Issue Activity (beta)

#244 Any way to run multiple clients concurrently?

#359 🎆 [Enhancement] Any plan or advice on adding `flash_attn` support?

#499 ChatterboxTurboTTS fails with RuntimeError: expected scalar type Double but found Float when specifying audio_prompt_path when numpy>=2.0

#552 CUDA graphs for T3 decode (~2x at batch 1)

#551 V3 doesn't appear to work as well as V2

#181 Provide a wrapper method that can take long lines to text and work around the 1000 token / 40 second limit

#549 Token-repetition check only looks at 2 tokens but comment and log say 3x

#548 Short-text crash in AlignmentStreamAnalyzer: IndexError on max(dim=1) when text has 5 or fewer tokens (root cause for #201, #435)

#550 Feature request: IPA / phoneme input support + improved pronunciation consistency

#546 Make `spacy-pkuseg` an optional extra — it is the only thing blocking Python 3.14 installs

#519 long_tail detection triggers too early, causing token repetition before forced EOS

#543 Chatterbox Turbo generation becomes unstable after ~25-30 seconds

#508 Chatterbox randomly takes forever to generate TTS

#541 How to build a Turkish Turbo 350m model

#198 TypeError: 'NoneType' object is not callable when initializing ChatterboxTTS

#524 Feature: Consider FunASR/SenseVoice for training data annotation

#522 Does this support Indonesian language?

#540 تجربة

#539 Excuse me, have you considered supporting Thai and Vietnamese?

#537 Chatterbox in native C++/GGML, 6.68x faster than real time

#517 Language request: Catalan (ca)

#536 BUG: Persistent low-level background tone/hiss in generated audio (~4900 Hz + elevated silence floor), traced to the vocoder, not the input

#271 Extra noise at the end of the generated clip

#535 Feature: chatterbox vllm real-streaming support

#534 Feature Request: Add CLI support for TTS, Turbo, Multilingual, and Voice Conversion