SpeechAvailable now

Kokoro

Give your applications a voice.

Expressive voices without heavy infrastructure: 82M TTS, 54 voices, 8 languages, fast and efficient under Apache-2.0.

Start Building Compare with the flagships Hugging Face model card

Good for

01Create voice assistants, narration and interactive experiences.
02Generate audio for learning, accessibility and customer service.
03Voice response and phone-menu systems (IVR).

Voice apps
Helpdesk & support
Marketing & content

Key facts

Model origin: Hexgrad
Size: 82M
Modalities: text → audio
Languages: 8
Voices: 54
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

TranscriptionAvailable nowWhisper large v3Multilingual speech transcription ChatAvailable nowQwen 3.8Enterprise chat, coding & 1M context ChatAvailable nowGemma 4Efficient AI for everyday workflows

More models

Qwen 3.8 Gemma 4 Clef FLUX.2 [klein]Whisper large v3 mxbai-embed-large v1 Qwen3 Embedding 0.6B 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