Breeze TTS 2: Text to Speech
Turn a script into speech with Breeze TTS 2: English and Chinese plus a 51-language mode, a voice cloned from a three-second sample, and inline audio tags.
Try an example
About this workflow
Breeze TTS 2 is Breeze Blue's open-weight voice model: English and Chinese natively, plus a 51-language multilingual mode. Speak a script in a featured voice, a voice cloned from a three-second recording, or one designed from a written description, and direct the performance in plain language or with inline audio tags such as (sighs) or (laughs), which are performed rather than read.
Graph: LoadAudio → BreezeVoiceClone → PreviewAny (the reusable voice id) → BreezeVoiceSelector (custom, driven by that id) → BreezeTextToSpeech (text up to 1000 characters, language English on Breeze TTS 2, delivery neutral, speed 1, seed randomized) → SaveAudioAdvanced writing FLAC. A SaveText keeps the voice id for reuse.
Two tools ship parked at mode 4: BreezeVoiceRemix (a changed copy of a voice you already have) and BreezeVoiceDesign (a new voice invented from words). Enable with Ctrl+B.
Related workflows
- ACE-Step
ACE Step v1 M2M Editing
- ACE-Step
ACE-Step 1.5 Music Generation (4B LLM )
- ACE-Step
ACE-Step 1.5 Music Generation AIO
- ACE-Step
ACE-Step 1.5 Music Generation Workflow
- ACE-Step
ACE-Step 1.5XL Base: Text to Music
- ACE-Step
ACE-Step 1.5XL SFT: Text to Music
- ACE-Step
ACE-Step 1.5XL Turbo: Text to Music
Audio Separation
- Chatter Box
Chatter Box: Multi-Speaker Conversation with Cloned Voices
- Chatter Box
Chatter Box: Multilingual Text-to-Speech with Voice Cloning
- Chatter Box
Chatter Box: Voice Cloning Audio Conversion
- Chatter Box
Chatter Box: Voice Cloning with TTS