Kosmik: Supertonic 3

Canonical model ID: kosmik/tts-supertonic-3

Multilingual speech synthesis. WAV output, speed 0.5–2. Use a language-prefixed voice such as en:M1 or cs:F1; unprefixed voices default to Czech. Quality uses 8 steps. Use is subject to the Open RAIL-M license and restrictions: https://api.koscompute.com/docs/security/speech-model-licenses/

Runtime metadata¶

This table is generated from public model metadata. Readiness and capacity are refreshed from GET /v1/models on page load.

Speech limits¶

Maximum input: 4,000 characters per request.

Default voice: M1.

License and usage¶

Review the speech model licenses and usage terms before calling this model.

Voices¶

Use this model¶

Copy the canonical ID into the model field. Check the endpoint guide before using optional capabilities.