Hormouz AIHormouzSign in

Text-to-speech (TTS) models

Text-to-speech (TTS) models on Hormouz. 36 of them, including ByteDance Seed: Seed Audio 1.0. Turn text into natural speech through one API.

  1. 1ByteDance Seed: Seed Audio 1.0ByteDance Seed · audio$0.15/minute of audio
  2. 2Canopy Labs: Orpheus 3BCanopylabs · audio$15/M characters
  3. 3Deepgram: Aura-2Deepgram · audio$30/M characters
  4. 4Deepgram: Flux TTSDeepgram · audio$45/M characters
  5. 5ElevenLabs: Eleven Flash v2Elevenlabs · audio$40/M characters
  6. 6ElevenLabs: Eleven Flash v2.5Elevenlabs · audio$40/M characters
  7. 7ElevenLabs: Eleven Multilingual v2Elevenlabs · audio$80/M characters
  8. 8ElevenLabs: Eleven Turbo v2Elevenlabs · audio$40/M characters
  9. 9ElevenLabs: Eleven Turbo v2.5Elevenlabs · audio$40/M characters
  10. 10ElevenLabs: Eleven v3Elevenlabs · audio$80/M characters
  11. 11ElevenLabs: Eleven v3 ConversationalElevenlabs · audio$40/M characters
  12. 12ElevenLabs: Eleven v4Elevenlabs · audio$80/M characters
  13. 13ElevenLabs: Eleven v4 TurboElevenlabs · audio$40/M characters
  14. 14Fish Audio: Drama 3Fish Audio · audio$10/M UTF-8 bytes
  15. 15Fish Audio: S1Fish Audio · audio$15/M UTF-8 bytes
  16. 16Fish Audio: S2 ProFish Audio · audio$15/M UTF-8 bytes
  17. 17Fish Audio: S2.1 ProFish Audio · audio$15/M UTF-8 bytes
  18. 18Fish Audio: S2.1 Pro Free (free)Fish Audio · audioFree
  19. 19Google: Gemini 3.1 Flash TTS PreviewGoogle · audio$1/M text tokens · $20/M audio tokens
  20. 20Google: Gemini 3.8 Flash Lite TTSGoogle · audio$0.5/M text tokens · $6/M audio tokens
  21. 21Google: Gemini 3.8 Flash TTSGoogle · audio$0.5/M text tokens · $9/M audio tokens
  22. 22hexgrad: Kokoro 82MHexgrad · audio$4/M characters
  23. 23Microsoft AI: MAI-Voice-2Microsoft · audio$22/M characters
  24. 24Microsoft AI: MAI-Voice-2-FlashMicrosoft · audio$15/M characters
  25. 25Microsoft AI: MAI-Voice-2.1Microsoft · audio$22/M characters
  26. 26Microsoft AI: MAI-Voice-2.1-FlashMicrosoft · audio$15/M characters
  27. 27MiniMax: Speech 2.8 HDMiniMax · audio$100/M characters
  28. 28MiniMax: Speech 2.8 TurboMiniMax · audio$60/M characters
  29. 29Mistral: Voxtral Mini TTSMistral AI · audio$16/M characters
  30. 30OpenAI: GPT-4o mini TTSOpenAI · audio$0.6/M text tokens · $12/M audio tokens
  31. 31OpenAI: TTS-1OpenAI · audio$15/M characters
  32. 32OpenAI: TTS-1 HDOpenAI · audio$30/M characters
  33. 33Qwen: Qwen-Audio-3.0-TTS FlashQwen · audio$15/M characters
  34. 34Qwen: Qwen-Audio-3.0-TTS PlusQwen · audio$20/M characters
  35. 35Sesame: CSM 1BSesame · audio$7/M characters
  36. 36SpaceXAI: Grok Voice TTS 1.0xAI · audio$15/M characters

FAQ

How do I convert text to speech with Hormouz?
Use the audio/speech endpoint with one of the 36 TTS models listed here, such as ByteDance Seed: Seed Audio 1.0. One API key covers all of them.

Updated 2026-10-13