Studio / Model Library
Model Library
Every model family in Studio's catalog, with its endpoints, tasks and what is actually known about licence and provenance. Cataloged is not executable: Studio resolves availability per project.
492families1,500endpoints1,487input schemas8open-provenance
23 of 492 families · Text to Audio
- video28 endpointsLTX 2.3 QualityImage EditingImage to VideoLoRA Training+4Licence not stated
- audio24 endpointsStable Audio 3Music GenerationText to AudioLicence not stated
- audio11 endpointsElevenLabsEleven v3 speech with audio-tag emotion control across 70+ languages plus 10 more endpoints.Music GenerationSpeechText to AudioLicence not stated
- audio9 endpointsKokoro82M-parameter Kokoro TTS with 19 voices across 9 language endpoints.Text to AudioLicence not stated
- audio5 endpointsQwen 3 TTSText to AudioLicence not stated
- video4 endpointsKling Video V1Text to AudioVideo EditingLicence not stated
- audio3 endpointsChatterboxSpeechText to AudioMIT · Hugging Face
- video4 endpointsMirelo AI Sfx 1.6Text to AudioVideo to VideoLicence not stated
- image3 endpointsStable Audio 25Image EditingText to AudioLicence not stated
- audio2 endpointsDia TTS1.6B-parameter Dia TTS with multi-speaker tags, emotion control, and natural nonverbals.Text to AudioApache-2.0 · Hugging Face
- video2 endpointsMmaudio V2MMAudio V2 adds synced effects, music, and sound to video across 1-30 second spans.Text to AudioVideo to AudioLicence not stated
- audio2 endpointsResemble AI ChatterboxhdSpeechText to AudioLicence not stated
- audio2 endpointsTadaText to AudioLicence not stated
- audio3 endpointsByteDance V2Text to AudioLicence not stated
- audio1 endpointAlibaba Qwen Audio 3 TTSText to AudioLicence not stated
- audio1 endpointAsync TTS ProText to AudioLicence not stated
- audio1 endpointF5 TTSF5-TTS clones voices zero-shot from one sample with F5 and E2 architecture options.Text to AudioLicence not stated
- audio1 endpointGemini 3.1 Flash TTSText to AudioLicence not stated
- audio1 endpointGemini TTSText to AudioLicence not stated
- audio1 endpointIndex TTS 2Text to AudioLicence not stated
- audio1 endpointInworld TTSText to AudioLicence not stated
- audio1 endpointOrpheus TTSLlama-based Orpheus TTS with 8 empathetic voices for agents and audiobooks.Text to AudioLicence not stated
- audio1 endpointxAI TTSText to AudioLicence not stated
Source: Studio canonical catalog studio-fal-catalog-v2, sha 333e0a2021b1, Studio commit c8ef436831e2. Delivery for every family listed is fal.ai.