Category

Text-to-Speech Human Preferences (315K)

Provides 315,000 pairwise human-preference votes comparing 15 English TTS models over 300 operational prompts, with 4,500 high‑quality audio renders and structured vote/pair/prompt records for training or evaluating preference/reward models. Metadata under CC-BY-4.0; audio use governed by model providers' terms.

LFM3-Audio-2B

Handles text and speech input, producing text, speech, or both for streaming voice interaction, multilingual audio tasks, and spoken tool calls. Its 2B-parameter size targets local and edge use, not complex multi-step reasoning.

YuE2-3B

Generates full songs from lyrics and a style prompt, producing vocals and accompaniment and exporting editable symbolic scores for melody/chord control. Uses symbolic planning with agentic multi-turn editing and runs local 48 kHz inference on a 24GB GPU.

Confucius4-R2T2

Provides low-latency, true-streaming automatic speech recognition that emits append-only committed transcripts to avoid partial-result rollbacks. Supports configurable decoding chunks (80 ms–2 s), optimized for Chinese and English, and offers vLLM and transformers backends for real-time deployment.

yue2-mothersuperior-realaudio-tokenizer-v4

Encodes real audio into YuE2 semantic tokens and ships a matching NAR-branch LoRA so the YuE2 decoder renders realistic latents—enables tokenizing recordings, training artist LoRAs, and generating songs or covers. Includes an 8-layer tokenizer head and a rank-32 decoder LoRA; requires the YuE2 base models and GPU resources.

Audio8 ASR Infinite

Performs low-latency streaming speech-to-text, emitting one token per selectable 80/120/160 ms clock with configurable transcription delay and a 30s rolling KV cache for unlimited 24/7 transcription. Bilingual (zh/en) and includes semantic VAD.

Nemotron 3 Diarization

Performs speaker diarization (who spoke when) for live and recorded audio using an open-weight, 100M-parameter streaming-capable model that supports up to eight anonymous speaker channels, overlapping speech, chunked processing, and configurable latency for ASR integration.

Phonon-2

Transcribes English speech into punctuated, capitalized text — a 164 MB quantized ASR model that averages 5.21% WER across seven Open ASR Leaderboard sets. Optimized for on-device and CPU/GPU inference, with fast runtimes on Apple M5 and Docker/GPU support.

Whistle

On-device speech-to-text for short clips (up to 30s) in seven languages, yielding transcripts, word-level timestamps and per-frame speech embeddings in a single 16.9 MB model. Runs on the Needle CPU engine with 2–4 bit quantization, supports keyword biasing and returns empty transcripts for silence.

Alania Turkish Synthetic Speech

Provides 3,451 hours (2,051,810 clips) of AI‑generated 48 kHz Turkish speech with transcripts, spoken forms and per‑clip voice descriptions for TTS and ASR development. Includes 2,752 designed voices and is licensed CC BY 4.0 / CC BY‑SA 4.0 (attribution to PatientDesk AI required).

Fish Audio Drama 3

Generates directed, multi-character, long-form speech from text with natural-language directions and voice cloning. Built on a 35B MoE backbone (3B active per token) with a codebook multi-token-prediction decoder to enable multi-turn revision, infilling edits, streaming, and expressive control.

Audio8-TTS-Realistic-Air

Generates speech from text and can clone a voice from a reference recording without fine-tuning. Its 0.6B-parameter core supports 23 languages, though quality varies substantially by language.