Audio & Speech
Text-to-speech, voice cloning and audio generation models.
10 models. Endpoint: not available yet.
| Model | Pricing |
|---|---|
elevenlabs/text-to-dialogue-v3 | 8 credits / call |
elevenlabs/text-to-speech-multilingual-v2 | 15 credits / call (upstream 12 / per 1000 characters × 1.25) |
elevenlabs/text-to-speech-turbo-2-5 | 8 credits / call (upstream 6 / per 1000 characters × 1.25) |
gemini-omni-audio | 8 credits / call |
google/gemini-2-5-pro-tts | 8 credits / call |
google/gemini-3-1-flash-tts | 8 credits / call |
google/gemini-3-8-flash-lite-tts | 8 credits / call |
google/gemini-3-8-flash-tts | 8 credits / call |
infinitalk/from-audio | 8 credits / call |
wan/2-2-a14b-speech-to-video-turbo | 8 credits / call |