VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Python aiaudiobookcudadubbingelevenlabs-alternativehuggingfacelocal-firstmlxomnivoice-studiospeech-to-texttext-to-speechtranscriptiontranslatettsvoice-aivoice-cloningvoice-generationvoicestudioworkflow
build(mlx): require mlx-audio 0.4.4+ for VoxCPM2 support
velixio5bc666b82315
diff --git a/pyproject.toml b/pyproject.tomlindex c8ff43590..d820b4f15 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -84,7 +84,7 @@ dependencies = [# Qwen3-TTS, Chatterbox, MeloTTS, OuteTTS, Spark, Higgs-Audio, Voxtral,# …). Gives mac-ARM users a broad engine picker in Settings. Also gated# by platform markers because it depends on mlx (Apple Silicon only).- "mlx-audio>=0.3.0 ; sys_platform == 'darwin' and platform_machine == 'arm64'",+ "mlx-audio>=0.4.4 ; sys_platform == 'darwin' and platform_machine == 'arm64'",# Apple Silicon-only Parakeet TDT v3 ASR (mlx-community/parakeet-tdt-0.6b-v3# via MLX). Gives mac-ARM the Parakeet tier CUDA/CPU users get from# sherpa/NeMo: 25 European languages, TDT token/word timestamps, ~2 GBdiff --git a/uv.lock b/uv.lockindex 880a8e192..1ba3ab1fb 100644--- a/uv.lock+++ b/uv.lock@@ -4274,7 +4274,7 @@ requires-dist = [{ name = "lightning", specifier = ">=2.6.6" },{ name = "litellm", specifier = ">=1.103.0,<2" },{ name = "mcp", specifier = ">=1.28.1,<2" },- { name = "mlx-audio", marker = "platform_machine == 'arm64' and sys_platform == 'darwin'", specifier = ">=0.3.0" },+ { name = "mlx-audio", marker = "platform_machine == 'arm64' and sys_platform == 'darwin'", specifier = ">=0.4.4" },{ name = "mlx-whisper", marker = "platform_machine == 'arm64' and sys_platform == 'darwin'", specifier = ">=0.2.1" },{ name = "num2words", specifier = ">=0.5.14" },{ name = "numpy" },