Models
Kosmik: Piper TTS Fast
Capabilities, limits, pricing, and endpoints for kosmik/tts-piper-fast.
Canonical model ID: kosmik/tts-piper-fast
Fast English speech synthesis with the LJSpeech voice. WAV output. The Czech Jirka voice is unavailable pending clarification of upstream training-model licensing; use Supertonic for Czech.
Runtime metadata¶
This table is generated from public model metadata. Readiness and capacity are refreshed from GET /v1/models on page load.
| Property | Value |
|---|---|
| Kind | audio-speech |
| Input | text |
| Output | audio |
| Context | Not token-based |
| Maximum output | Endpoint-specific |
| Supported endpoints | /v1/audio/speech |
| Capabilities | Endpoint-specific |
| Pricing | $0.50 per 1M characters |
Speech limits¶
Maximum input: 4,000 characters per request.
Default voice: en_US-ljspeech-high.
License and usage¶
Review the speech model licenses and usage terms before calling this model.
Voices¶
| Voice ID | Language | Name |
|---|---|---|
en_US-ljspeech-high |
en-US | LJSpeech (English) |
Use this model¶
Copy the canonical ID into the model field. Check the endpoint guide before using optional capabilities.