TranscriptionAvailable now

Whisper large v3

Every word matters. Capture them all.

Transcribe ~100 languages and translate them into English, trained on 5M+ hours to handle accents and noisy audio.

Start Building Compare with the flagships Hugging Face model card

Good for

01Transcribe meetings, calls, podcasts and videos.
02Create searchable subtitles and timestamped transcripts.
03Translate multilingual speech into English.

Meetings & calls
Helpdesk & support
Documentation

Key facts

Model origin: OpenAI
Size: 1.55B
Modalities: audio → text
Languages: 99
API model id: Model id published at launch
Availability: Available now. Regional rollout is shown in your Console. Ask us about your region.

Your data boundary

Prompts and outputs are not stored by default. Knowledge or Memory data that your organization intentionally persists is encrypted, pinned to the selected region, isolated to authorized organizational scopes, and never used to train shared or third-party models.

Works well with

ChatAvailable nowQwen 3.8Enterprise chat, coding & 1M context SpeechAvailable nowKokoroNatural, low-latency speech generation EmbeddingsAvailable nowQwen3 Embedding 0.6BMultilingual search across 100+ languages

More models

Qwen 3.8 Gemma 4 Clef FLUX.2 [klein]mxbai-embed-large v1 Qwen3 Embedding 0.6B Kokoro DeepSeek 4.1 Flash GLM 5.3

Explore the platform

Start with control

Create your account and pick the region your data must stay in.

Create account Talk to us