Media providers
Provider index for image, speech, transcription, and video models.
Media models are first-class provider types, not language-model wrappers. Each conforms to one focused protocol and plugs into its matching top-level function.
Image generation
| Provider | Model type |
|---|---|
| OpenAI | OpenAIImageModel |
| fal | FalImageModel |
| Luma | LumaImageModel |
| Replicate | ReplicateImageModel |
See image generation for the shared API.
Speech generation
| Provider | Model type |
|---|---|
| OpenAI | OpenAISpeechModel |
| ElevenLabs | ElevenLabsSpeechModel |
| LMNT | LMNTSpeechModel |
| Hume | HumeSpeechModel |
| Deepgram | DeepgramSpeechModel |
| Sarvam | SarvamSpeechModel |
See speech generation for the shared API.
Transcription
| Provider | Model type |
|---|---|
| OpenAI | OpenAITranscriptionModel |
| ElevenLabs | ElevenLabsTranscriptionModel |
| Deepgram | DeepgramTranscriptionModel |
| AssemblyAI | AssemblyAITranscriptionModel |
| Rev.ai | RevAITranscriptionModel |
| Gladia | GladiaTranscriptionModel |
| Sarvam | SarvamTranscriptionModel |
See transcription for the shared API. Groq-hosted
Whisper also works through OpenAITranscriptionModel with Groq's base URL.
Video generation
See video generation for the shared API.