Model reference · open weights

voiceclap-small

Available as managed deployment Licence fee Embeddings laion Embeddings 1 variants 2k dl/mo

voiceclap-small is an open-weight embedding model from laion. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bylaion
TypeEmbedding models
TaskEmbeddings
Parameters (lead)113M
Runs withtransformers
Based onlaion/voiceclap-small
Released2026-06-11
Popularity2k downloads / month
LicenceCommercial licence needed

About

What voiceclap-small is

Voice-text contrastive (CLAP-style) embedding model — the successor to laion/voiceclap-small, trained with emotion-led MOSS-Audio short captions. Better than v1 on every benchmark we measure, at identical size and inference cost.

Same dual-tower architecture as v1: a BUD-E-Whisper_V1.1 audio encoder paired with sentence-transformers/all-MiniLM-L6-v2 on the text side, joined by an MLP projection on each side and trained with the SigLIP sigmoid contrastive loss.

Read the full model card
Architecturedual-tower CLAP (BUD-E-Whisper-Small + MiniLM-L6-v2)
Audio encoderWhisper-style: 12 layers × 768 dim × 12 heads, 80-mel input @ 16 kHz
Text encoderBERT/MiniLM, 6 layers × 384 dim, mean-pooled
Joint embedding768-d, L2-normalised
LossSigLIP (sigmoid contrastive)
Total parameters~110 M
Training40 M samples (20 epochs × 2 M), best checkpoint epoch 19

What's new vs v1

v1 sampled k=2 uniformly-chosen MOSS-Audio attribute sentences per clip as the caption. v2 replaces this with an emotion-led short caption: the MOSS-Audio-8B-Thinking EMO sentence (a direct natural-language description of the emotional state) plus one randomly sampled talking-style sentence, re-drawn every epoch. Captions stay 50/50 blended with each corpus's original captions. The emotion-first structure concentrates contrastive signal on the emotion subspace without sacrificing style coverage.

Evaluation

Benchmarkv1 (released)v2 (this model)Δ
EmoNet-Voice top-10.09020.1015+13% rel
EmoNet-Voice Spearman ρ0.22800.2561+12% rel
MAEB-voice mean (8 tasks)0.38610.3893+0.8%

The ρ gain also clears every arm of the v1 caption-sampling sweep (best: 0.2399 at k=2). MAEB-voice shows no general-speech regression.

Training data

Trained on the open 9-corpus mixture used in the VoiceNet paper:

  • emolia-balanced-5M-subset (annotated subset of Emilia)
  • laions_got_talent_clean_with_captions
  • majestrino-data
  • synthetic_vocal_bursts + improved_synthetic_vocal_bursts
  • ears, expresso, voxceleb1, voxceleb2 (FCaps captions)

MOSS-Audio-8B-Thinking annotations (18 prompt groups, 61 attribute values per clip) provide the EMO + style sentences for the three large corpora.

Usage

import torch
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("laion/voiceclap-small-v2", trust_remote_code=True).eval()
tok = AutoTokenizer.from_pretrained("laion/voiceclap-small-v2")

# audio: raw mono waveform at 16 kHz
import soundfile as sf
wav, sr = sf.read("clip.wav", dtype="float32")
audio_emb = model.encode_waveform(torch.from_numpy(wav))

# text
t = tok(["a person speaking with quiet pride in their voice"], padding=True, return_tensors="pt")
text_emb = model.encode_text(t["input_ids"], attention_mask=t["attention_mask"])

score = (audio_emb @ text_emb.T).item()

Conversion from the training checkpoint was verified functionally against the original open_clip implementation (cosine ≥ 0.9999 on both towers).

Sibling models

License

cc-by-nc-4.0

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys voiceclap-small for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (voiceclap-small below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"voiceclap-small","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms