laion/Humaneness-Voice-Large-1.7

Humaneness Voice Large 1.7

Expressive speech in English, German, French, Spanish and Dutch.

Write the words and direct the performance: emotion, conversational delivery, pauses and vocal reactions. Use a clean reference recording to guide the speaker identity, or generate a voice without a reference.

▶ Watch the video: Humaneness Voice Large 1.7

Listen and find your prompting recipe

Start here	What you will find
🎧 Five-language acting grid	Browse acting scenarios, listen to generated performances and inspect their prompts.
📖 Prompting guide — the basic format	Learn GENERAL: / SCRIPT:, inline directions, vocal bursts, timing, references and CFG. Start here to write your first prompt.
🧪 Interactive 1.7 prompting manual with audio	Find searched recipes for 40 emotions, 15 talking styles and 18 vocal-burst classes in five languages. Hear selected recipes beside matched baselines, compare all six held-out takes and copy exact prompts and CFG settings.
🤖 Agent reference · Machine-readable recipes	Read the input contract and retrieve configurations by target and language. Only usable: true identifies a recipe that passed the declared held-out gates.
📊 Matched checkpoint comparison	Compare checkpoints and CFG settings; inspect evaluation audio and recorded scores.

The manual covers 455 target/language/condition combinations. Its main audio players are visible directly; starting a clip pauses the others. Expand a condition for the remaining test takes, exact instructions and CFG comparison. Exploratory results are labelled, so an audible example is not automatically a validated recommendation.

Prompting in one minute

Pass two separate inputs: text is exactly what should be spoken; prompt describes how to perform it. The standard format is:

GENERAL: A natural, close conversation. The speaker is trying to contain
strong anger rather than turning the whole line into a shout.
SCRIPT:
(intensely angry, held back) [3.2 seconds duration] You knew what this meant to me.
[0.4 seconds pause]
(quieter, the anger still present) [2.5 seconds duration] And you did it anyway.

The separate text is:

You knew what this meant to me. And you did it anyway.

• GENERAL: describes the overall voice, scene and audible delivery.
• SCRIPT: repeats the spoken words and places directions at the relevant beat.
• Round parentheses contain local delivery or non-speech reactions, such as (quietly angry) or (sharp gasp, 0.3 seconds). Keep these out of text.
• Square brackets can request duration and pauses. Some searched recipes instead place duration inside round parentheses; copy the recorded recipe's syntax when reproducing its results.
• Keep performance instructions in English where practical; dialogue can be in any of the five supported languages.

Requested timing is learned conditioning, not a guaranteed editing boundary. For masking, hesitation, vocal bursts and complete examples, read the prompting guide. To choose wording and CFG for a particular emotion or style, use the interactive manual.

Quick start

This repository contains complete merged 1.7 weights. Ordinary inference does not require attaching an adapter.

Install a CUDA-enabled PyTorch build for your server, then the dependencies:

hf download laion/Humaneness-Voice-Large-1.7 --local-dir humaneness-large17
cd humaneness-large17
pip install -r requirements.txt
python infer.py --language en --seconds 9.2 --seed 1701 \
  --text 'I thought you had forgotten. You remembered every little detail. I am so glad you came back.' \
  --prompt-file examples/prompt-en.txt --output example.wav

The custom implementation requires trust_remote_code=True; review the code before loading. Root weights are stored in FP32. The supplied inference loader uses BF16 weights and compute. The separate MOSS Audio Tokenizer v2 retains its upstream terms.

Add a reference voice

Add --reference-wav clean-speaker.wav to the command above. Use clean speech from one speaker, with different words from the requested output. Supply at least 5.04 seconds; the helper crops the waveform to 14.96 seconds before encoding. It does not use the historical 2.96-second cap. Reference audio guides identity but does not guarantee exact voice preservation.

For repeated requests, keep the model and codec resident:

from pathlib import Path
import infer

model, processor, api = infer.load()
api.load_codec(processor, "OpenMOSS-Team/MOSS-Audio-Tokenizer-v2")
reference = infer.reference_codes(processor, Path("clean-speaker.wav"))

codes = infer.generate_codes(
    model, processor, api,
    text="I am so glad you came back.",
    prompt="GENERAL: Warm, natural relief.\nSCRIPT:\n"
           "(quiet relief) [3.0 seconds duration] I am so glad you came back.",
    seconds=3.0, language="en", seed=1701, reference=reference,
)
waveform, sample_rate = api.decode(processor, codes)

Adjust classifier-free guidance

For a guided take, try:

python infer.py --language en --seconds 9.2 --seed 1701 \
  --text 'I thought you had forgotten. You remembered every little detail. I am so glad you came back.' \
  --prompt-file examples/prompt-en.txt \
  --cfg 2.5 --neutral-prompt-file examples/neutral-en.txt \
  --output example-cfg.wav

The neutral branch must keep the same literal words, durations and reference; remove only the emotional/style treatment. CFG 1 means guidance off. CFG 2.5 is the acting showcase setting, not an optimum for every condition. The manual reports condition-specific CFG searches. Those searches used the merged 1.7 model without reference audio or extra adapters; preserve that setup when reproducing them.

Use the manual as a person or an agent

Choose a language and an emotion, talking style or vocal-burst condition in the interactive manual. Listen to the selected recipe and paired baseline, then inspect the exact conditional and neutral prompts. All six held-out takes remain available, including failures; recipe selection does not cherry-pick a test recording.

For programmatic use, start with manual/AGENT_GUIDE.md and manual/recipes.jsonl. Match the target, language and, for vocal bursts, surrounding-emotion condition. Check usable and the evidence status before treating a recipe as a recommendation. The linked evidence preserves prompts, sampling settings, raw scores and audio.

The earlier 1.5/1.6 manuals document different weights. Their specialist adapters and preferred CFG values are historical evidence; use the 1.7 manual above for this model's measured recipes.

What is included

Location	Purpose
Root config, tokenizer and safetensors shards	Complete merged 1.7 model; no adapter required
PROMPTING.md	Basic human-readable prompting guide
manual/	Agent guide and machine-readable search recipes
infer.py	Reference inference, optionally with a speaker reference or CFG
INFERENCE_OPTIMIZATIONS.md	Batching, true logit CFG and throughput guidance
adapter/adapter.safetensors	Original selected rank-32 adapter, update 44,250
parent_model/	Exact High-8654 parent, rounded to BF16 as in the original evaluation
runtime/native_adapters.py	Original custom FP32 residual adapter implementation; not PEFT
runtime/native_cfg.py	Evaluated twelve-channel logit CFG implementation
training/	Portable reference trainer, recipes and original training snapshots
TRAINING.md · provenance.json	Training history and exact model provenance
stats/ · examples/canary/	Selection evidence, merge audit and canary audio

Do not apply the included adapter to the merged root model again. For the original unmerged arithmetic, python infer.py --unmerged ... loads parent_model/ plus the adapter exactly once. This native control is useful because merging changes BF16 rounding and can change sampled speech.

Training and model lineage

1.7 combines the Acting High-8654 supervised checkpoint with its selected rank-32 acting adapter at update 44,250, scale 1.0. This is a supervised branch from Large 1.3 Alpha. It does not contain the 1.4/1.5 RL adapter stack and is not Large 1.6 with another adapter attached.

The 1.3 ancestor first received a full supervised acting continuation. The High-8654 checkpoint then received a rank-32 adapter trained on a per-language union of top 1% emotion/style takes and top 2% genuineness-plus-blend takes. The adapter schedule ran for three epochs; 1.7 selects update 44,250 rather than the final 58,944. Training covers EN, DE, FR, ES and NL. See TRAINING.md for source mixture weights and the full recipe.

To fine-tune with compatible data, start with training/train_reference.py.

Architecture

The hierarchical MOSS Local Transformer TTS model has 4,129,990,144 unique base parameters: a Qwen3-family semantic transformer and a local Talker. Each 80-ms frame produces 12 indices, one per codec codebook, each with 1,024 possible values: 12.5 frames/s × 12 = 150 codec indices/s. The separate codec returns 48-kHz mono audio. The model does not generate all 32 codec books.

Checkpoint selection results

Seven second-half adapter checkpoints were compared on the same 108 English/ German tasks: 40 emotions and 14 edge cases, one seed, no reference, CFG 1. Update 44,250 had the highest frozen composite among the seven complete matrices:

Development-selected update 44,250	Mean
Content Enjoyment, EARS predicted score	6.3334
Genuineness, EARS 0–6	4.2565
Vocal Burst Blend, EARS 0–10	7.7503
Requested emotion/style CDF diagnostic	0.58566
Composite: 40% target + 30% CE/10 + 30% genuineness/6	0.63709
Mean per-clip ASR word error rate	0.05787%

The target diagnostic is not an accuracy percentage. WER is the arithmetic mean of per-clip rates, not a corpus-token-weighted rate. Scores are model predictions, not human listening ratings. The selected state does not maximize every metric. This was development selection among seven checkpoints, not an independent held-out confirmation. See stats/selection.json for the selection record and paired uncertainty.

Those selection recordings use the original unmerged BF16-parent/FP32-LoRA path. FP32 merging was checked algebraically. The merged BF16 deployment was then tested against that native control on one fixed script in each language and one English CFG 2.5 pair. Every take is retained. The merge audit does not claim bit-identical sampled tokens or establish quality gains from five scripts. You can also hear the canary audio or download its listening HTML.

The separate 1.7 evolutionary manual tests recipes on the merged model; its held-out recipe evidence should not be confused with the checkpoint selection study above.

Throughput and streaming

Reuse a resident model and codec, cache reference codes and batch compatible candidate generations. Best-of-N selection must finish its candidates before choosing a winner. Streaming latency and offline throughput are separate goals.

The Humaneness-Voice server contains batching, streaming and optional graph/kernel optimizations. Its published 0.16-second onset is a Small-model Jetson Thor result, not a 1.7 measurement. This release provides a full-utterance reference path and batched same-condition CFG helper; it does not claim that every historical server or CUDA graph is validated for 1.7. Read the inference and optimization guide before reporting speed measurements.

License and use

New model contributions and release materials are CC BY 4.0. Keep NOTICE.md and upstream notices. External codecs, software and training datasets retain their own terms. CC BY does not grant rights over another person's identity. Use consented references, identify synthetic material appropriately and test the model before deployment.