Voxta docs

audio.cpp

Local text-to-speech, speech-to-text and music without Python, run by audio.cpp on a CUDA GPU. Kokoro, Chatterbox, Fish Audio S2, OmniVoice, VibeVoice, BreezeTTS 2, Parakeet, Nemotron, ACE-Step and more.

The audio.cpp module runs GGUF audio models through audio.cpp's own server (audiocpp_server). It needs no Python and runs one process per loaded model, so a crash ends that server and not Voxta. One module has three services, each its own card in Add Modules:

ServiceDoes
audio.cpp Text to SpeechVoices: built-in, cloned from a sample, or designed from a description.
audio.cpp Speech to TextSpeech transcription and clip transcription.
audio.cpp MusicSongs and instrumentals by ACE-Step 1.5.

Experimental and admin-only. CUDA only, on Windows and Linux x64: Voxta downloads the server and its CUDA runtime on demand.

Setup

Add the service

Add Modules → Services → audio.cpp Text to Speech (or audio.cpp Speech to Text, audio.cpp Music) → Install, then follow the install steps.

Pick a model

In the install flow's Models step. Each service loads one model. You can also type a Hugging Face reference to any audio.cpp GGUF, or drop one in the models directory. Model Family is detected from the file. Set it only for a model audio.cpp cannot identify.

GPU Index picks the card when there is more than one. CPU Threads sets threads for the parts that run on the CPU.

Text to speech

ModelVoicesStreamsVideo memory
BreezeTTS 2 (default)Clones a sampleYes~4.5 GB
Kokoro 82MBuilt-inYes~1.6 GB
Kitten TTS 2Built-in (Bella, Bruno)No~3.5 GB
Chatterbox TurboOne voice of its own, refuses a sampleNo~0.9 GB
Chatterbox MultilingualClones a sample, needs oneNo~1.8 GB
Fish Audio S2 ProClones a sampleYes~7 GB
Fish Drama 3Clones a sampleYes~18 GB
OmniVoiceClones a sampleYes~0.6 GB
VibeVoice 1.5B / 7BClones a sampleYes~2.8 / ~11 GB
Echo-TTSClones a sample, needs oneNo~7.5 GB

A streaming model's audio is sent as it is generated. The others send each line when it is done. Models that clone use the voice library and the character's voice sample. Several also use the sample's transcript. Default Female / Male Voice apply to the models with voices of their own.

Voice design

With BreezeTTS 2 or OmniVoice loaded, the service can design a voice in the Voice Studio. BreezeTTS 2 reads a description as written. OmniVoice takes a pick from its lists: gender, age, pitch, whisper style and accent.

Delivery

How a line is told its emotion tag depends on the model:

ModelDelivery
Cloning modelsAffect clips recorded beside the voice file.
Fish Audio S2, Fish Drama 3Clips, plus a bracketed tag in front of the line: [sad].
BreezeTTS 2Clips, plus the direction as an instruction.
Kokoro, Kitten TTS 2, Chatterbox TurboNone.

The offered words are Delivery Directions (advanced), in the same shape as Fish Audio's audio tags: sad, laughing=decay(excited), moaning=repeat([moaning, panting, breathy], 4..9). Allow Unrestricted Directions (on by default) lets the AI write its own, like through gritted teeth, which Fish and BreezeTTS read as free-form directions.

Speech to text

ModelCoversVideo memory
Parakeet TDT 0.6B v3 (default)25 European languages~0.8 GB
Fun-ASR-Nano 2512Chinese, Japanese and more~1.3 GB
Qwen3-ASR 0.6B / 1.7BChinese, Japanese and more~1.4 / ~2.8 GB
Nemotron 3.5 ASR Streaming 0.6BGives each word as it hears it~1.0 GB

The other models re-read what you have said so far every Partial Interval (ms) (default 500, 0 turns partials off) and read it whole when you pause. Nemotron streams its words instead, and its final transcript is still read whole so it is punctuated. Max Segment Length (s) (default 30) finishes long stretches of speech without waiting for a pause.

Music

ACE-Step 1.5 in one GGUF file holding the music model, the planner, the text encoder and the audio decoder.

ModelNotes
ACE-Step 1.5 Turbo (Q8_0) (default)8 steps.
ACE-Step 1.5 Turbo (BF16)
ACE-Step 1.5 Base (Q8_0)30 to 50 steps, more detail.

About 8 GB of video memory to make a song, 13 GB to repaint or remix one. It does Generate, Repaint and Remix. Takes, up to 4, are made one after the other. Length 10–600 s (default 120), BPM, key, beats per bar and a negative style are supported. There are no stems or LoRAs. Planner Thinking (on by default) lets the planner reason about structure, tempo and key first. For the Python version, with presets and LoRAs, see ACE-Step.

On this page