Open model
Models
1,496models
511families
84labs
ImageVideoAudio3DTextData (JSON)File
Results
A card opens the endpoint that matches your filters; the variant count on it lists the family's other endpoints.Open model
Speech-to-Text · Turbo · Stream
Speech to Text $0.0008 / second of input audio 0.8 API credits / second of input audio · ≈ ₽0.09OpenAI
Wizper (Whisper v3)
Speech to Text $0.00111 / second of processing time 1.11 API credits / second of processing time · ≈ ₽0.12 typical run ≈ $0.009Open model
DiffRhythm: Lyrics to Song
Text to Music $0.001 / second 1 API credit / second · ≈ ₽0.11 100 s ≈ $0.10Open model
DeepFilterNet 3
Audio $0.001 / second of input audio 1 API credit / second of input audio · ≈ ₽0.11xAI
Grok Voice
Audio $0.00083 / second of the voice session 0.83 API credits / second of the voice session · ≈ ₽0.09 typical run ≈ $0.006Mirelo AI
Mirelo SFX2.0
Video to Video · Audio +1 $0.01 / second of output audio 10 API credits / second of output audio · ≈ ₽1.07ByteDance
Seed Audio 1.0
Audio $0.1875 / minute of generated audio 187.5 API credits / minute of generated audio · ≈ ₽20.12 typical run ≈ $0.023Tencent
Hunyuan Video Foley
Video to Audio $0.10 / 10 seconds of input video 100 API credits / 10 seconds of input video · ≈ ₽10.73No models match these filters
Clear filters