AI NEWS.ccAI is happening. The future is updating.
♡ Saved tools 0
AI NEWS · Model intelligenceExplore capabilities. Make informed choices. ↗Profiles indexed first · Details continuously enriched
THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Popular searches
84,999 model profiles13202 providers / publishers45 capability categories465 with comparable prices · 30 benchmarked
TText generation▧Image generation▷Video generation⌘Code generation◖Speech synthesis♫Music generation⬡3D modeling▤Document analysis
DISCOVER & COMPARE

Explore AI models 84999

Discover models worth your attention

GGUF conversions of ibm-granite/granite-speech-4.1-2b-nar for use with transcribe.cpp. Ported from upstream commit 99a4df9, pinned 2026-05-24. Validated against the Transformers reference at transcribe.cpp commit c53af2c on 2026-05-24. Offline multilingual speech-to-text in a single non-autoregressive editor pass. IBM Granite Speech 4.1-2b NAR shares the Conformer audio encoder with the AR Granite-Speech family but pairs it with a custom MLP-with- attention projector and the Granite-4.0-1b LLM used as a bidirectional editor (causal mask disabled). One forward pass produces logits over the full transcript; CTC decode yields the final text. No token-by-token loop. Takes a 16 kHz mono WAV and produces a transcript. English plus French, German, Spanish, and Portuguese; ASR only (no translation, no timestamps).

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Ported from upstream commit edd3bf5, pinned 2026-05-17. Validated against the Transformers reference at transcribe.cpp commit 275332d on 2026-05-17. Offline multilingual speech-to-text with word-level timestamps. IBM Granite Speech 4.1-2b-plus is the timestamp-and-diarization variant of the Granite-Speech family. Same architecture as the base 4.1-2b (Conformer encoder, BLIP-2 Q-Former projector, Granite-4.0-1b autoregressive LLM decoder) with two changes: the encoder concatenates mid-layer (idx 3) and final-layer hidden states (`cat_hidden_layers=[3]`, doubling the projector K/V input from 1024 to 2048), and the LM token embeddings are tied with the lm_head. Takes a 16 kHz mono WAV and produces a transcript, with `--timestamps word` returning structured per-word timestamps (parsed from the model's `[T:N]` centisecond markers), or `--diarize` returning structured speaker-attributed turns from its separate SAA prompt. Those two prompt tasks cannot be combined. Transcribes English, French, German, Spanish, and Portuguese (no Japanese on this variant). This variant is transcription-only: unlike the base granite-speech-4.1-2b, it does not perform speech translation. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Ported from upstream commit 0253049, pinned 2026-10-05. Validated against the SpeechBrain reference at transcribe.cpp commit aa4d0f47 on 2026-10-08. Spoken language identification over 107 languages: SpeechBrain's ECAPA-TDNN trained on VoxLingua107. NOT a transcription model: a run returns the model's language labels ranked by probability, optionally restricted to a caller-chosen set. Takes 16 kHz mono WAV; scores up to the first 30 s of a clip. Top-1 accuracy on FLEURS multilingual (3,000 utterances), scored on cpu. Measured at transcribe.cpp `cf62265a` on 2026-10-08.

Audio processing
Input Audio→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Ported from upstream commit 57b8436, pinned 2026-05-06. Validated against the HF Transformers v5.7.0 reference at transcribe.cpp commit 0d312ce on 2026-05-06. English speech-to-text in both one-shot and streaming modes. An encoder-decoder ASR model designed for streaming use (ergodic encoder + sliding-window attention, 50 Hz time-domain frontend). Same family as moonshine-streaming-tiny and moonshine-streaming-small; deepest of the three (14 / 14 layers) and widest hidden dims (encoder 768 / decoder 640). Takes a 16 kHz mono WAV and produces a transcript. No translation, no multilingual capability, no timestamps. WER on the full LibriSpeech test-clean split (2,620 utterances). Figures without a commit were published before provenance was recorded.

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Ported from upstream commit 2c03650, pinned 2026-05-06. Validated against the HF Transformers v5.7.0 reference at transcribe.cpp commit 0d312ce on 2026-05-06. English speech-to-text in both one-shot and streaming modes. An encoder-decoder ASR model designed for streaming use (ergodic encoder + sliding-window attention, 50 Hz time-domain frontend). Same family as moonshine-streaming-tiny; deeper encoder/decoder (10 / 10 layers) and wider hidden dims (encoder 620 / decoder 512). Takes a 16 kHz mono WAV and produces a transcript. No translation, no multilingual capability, no timestamps. WER on the full LibriSpeech test-clean split (2,620 utterances). Figures without a commit were published before provenance was recorded.

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Ported from upstream commit d7231bb, pinned 2026-07-12. Validated against the MOSS author repo (OpenMOSS/MOSS-Transcribe-Diarize) reference at transcribe.cpp commit 3f5e15c on 2026-07-12. Offline English/Chinese speech-to-text with speaker diarization. A 0.9B audio-LLM: a Whisper-Medium encoder (24 layers, d_model=1024) feeds a 4x temporal merge + VQAdaptor bridge into a Qwen3-0.6B decoder (28 layers) via audio-token injection. The model emits `[start][Sxx]text[end]`; the runtime parses those generated markers into clean text and segment rows. Speaker attribution is opt-in (`--diarize`) and returns structured speaker ids/turns. Not a streaming model. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

GGUF conversions of nvidia/multitalker-parakeet-streaming-0.6b-v1 for use with transcribe.cpp. Ported from upstream commit 8749fc7, pinned 2026-07-12. Validated against the NeMo reference at transcribe.cpp commit 3083021 on 2026-08-03. Offline and cache-aware streaming English speech-to-text with punctuation and capitalization. A cache-aware streaming FastConformer encoder with an RNN-T transducer decoder, fine-tuned from nvidia/nemotron-speech-streaming-en-0.6b. Plain GGUFs run the single_speaker_mode ASR path, while bundle GGUFs embed nvidia/diar_streaming_sortformer_4spk-v2.1 and, with `--diarize`, transcribe up to four overlapping speakers into a speaker-tagged transcript. The encoder preserves the upstream att_context_size=[70, 13] (1.12s) cache-aware attention mask; all four latency lookahead settings are selectable.

Speech recognition
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗
COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ
How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

AI NEWS · From information to decisions

Follow trends. Find tools. Explore models.

Explore AI news ↗Discover AI tools ↗