What's New
- PocketTTS Streaming API (#369): Added streaming synthesis support for PocketTTS
- All 21 PocketTTS Voices (#375): Support for all upstream PocketTTS voices with on-demand download from HuggingFace
- Multilingual G2P Model (#367): Added grapheme-to-phoneme functionality supporting French, German, Spanish, Japanese, Chinese, Hindi with a FLEURS benchmark CLI command
Fixes
- Fixed SDK guard for
MLMultiArrayDataType.int8to use proper availability checks (#364) - Corrected licensing documentation from MIT to Apache 2.0 in PocketTTS (#361)
Docs
- Updated README highlights with TTS and streaming ASR info (#374)
- Added Kokoro English voice quality report (#373)
- Fixed CLI name references to fluidaudiocli (#372)
- Fixed stale references, versions, and missing CLI commands (#370)
- Enhanced text-processing-rs description to reflect multilingual capabilities (#365)
- Updated Kokoro TTS documentation, clarifying it remains actively maintained (#360)
- Added Meeting Transcriber to project showcase (#362)
- Added Enconvo to project showcase (#359)