GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dsinghvi
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
dsinghvi
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Use Python 3.11 and install the correct PyTorch build for your CPU or CUDA platform first. The versions in requirements.txt are the tested environment; if the pinned PyTorch wheel is unavailable for your platform, install the matching build from PyTorch and then install the remaining packages.
bash
python -m venv .venvsource .venv/bin/activatepip install -r requirements.txtAll speech outputs are 24 kHz WAV files. Reference audio is used for voice conditioning and may be WAV, FLAC, Opus, or another format supported by SoundFile/FFmpeg.
bash
# TTS in a supplied reference voicepython inference.py --task tts \ --reference-audio /path/to/reference.flac \ --text "The model is speaking this sentence." \ --output generated.wav # STTpython inference.py --task stt \ --audio /path/to/input.opus \ --output transcript.txt # Continue text as speech in a supplied reference voicepython inference.py --task text-speech-continuation \ --text "The first part of the document ends here." \ --reference-audio /path/to/reference.flac \ --output continuation.wav # Continue speech as textpython inference.py --task speech-text-continuation \ --audio /path/to/excerpt.opus \ --output continuation.txt # Continue speech as speechpython inference.py --task speech-speech-continuation \ --audio /path/to/excerpt.opus \ --output continuation.wavWhen the files are downloaded from Hugging Face into another directory, pass either that local directory or the repository ID:
bash
python inference.py --model ORG/REPOSITORY --task tts \ --reference-audio reference.flac --text "Hello." --output hello.wavUseful controls include --greedy, --temperature, --top-p, --repetition-penalty, --max-new-tokens, --device, and --dtype. --local-files-only prevents network access once both this model and the SNAC codec are cached.
Input audio uses SNAC levels 0 and 1 packed as three tokens per base frame inside <listen>...</listen>. Generated speech uses all seven SNAC code streams per base frame inside <speak>...</speak>. The tokenizer validates these reserved token IDs before loading the model, preventing accidental use with an incompatible tokenizer.
This is a research checkpoint, not a production speech system. TTS has produced audible outputs in project testing. STT and cross-modal continuation quality remain experimental and can be poor, repetitive, or silent for some prompts and references. Generated speech should be reviewed before use.
python -m venv .venvsource .venv/bin/activatepip install -r requirements.txt# TTS in a supplied reference voicepython inference.py --task tts \ --reference-audio /path/to/reference.flac \ --text "The model is speaking this sentence." \ --output generated.wav # STTpython inference.py --task stt \ --audio /path/to/input.opus \ --output transcript.txt # Continue text as speech in a supplied reference voicepython inference.py --task text-speech-continuation \ --text "The first part of the document ends here." \ --reference-audio /path/to/reference.flac \ --output continuation.wav # Continue speech as textpython inference.py --task speech-text-continuation \ --audio /path/to/excerpt.opus \ --output continuation.txt # Continue speech as speechpython inference.py --task speech-speech-continuation \ --audio /path/to/excerpt.opus \ --output continuation.wavpython inference.py --model ORG/REPOSITORY --task tts \ --reference-audio reference.flac --text "Hello." --output hello.wav