POST /v1/data/ai/speech/run
Pricing: Metered: you pay exactly each call’s cost at the selected model’s rates (default ElevenLabs: Eleven Flash v2.5: the model’s own rate).
Request
Send the inputs underparams. Only the keys below are accepted; any other key returns 422 invalid_params.
The texts to speak, one per line, up to 5,000 characters each. Each text is one call and one audio file.
The text-to-speech model. Pick from the list (popular models first). Each model shows its own rate, mostly per 1M characters, and that is exactly what each text costs.36 allowed values, for example
elevenlabs/eleven-flash-v2.5 (ElevenLabs: Eleven Flash v2.5), elevenlabs/eleven-v4 (ElevenLabs: Eleven v4), elevenlabs/eleven-v4-turbo (ElevenLabs: Eleven v4 Turbo), elevenlabs/eleven-v3 (ElevenLabs: Eleven v3), google/gemini-3.8-flash-lite-tts (Google: Gemini 3.8 Flash Lite TTS), minimax/speech-2.8-hd (MiniMax: Speech 2.8 HD), deepgram/flux-tts (Deepgram: Flux TTS), microsoft/mai-voice-2.1-flash (Microsoft AI: MAI-Voice-2.1-Flash), mistralai/voxtral-mini-tts-3-0 (Mistral: Voxtral TTS 3), assemblyai/assemblyai-tts-1 (AssemblyAI: TTS 1). Fetch the full list with GET /v1/data/ai/speech?expand=options.The voice, from the selected model’s own voices. Leave blank for the model’s first listed voice.612 allowed values, for example
george (george (ElevenLabs)), sarah (sarah (ElevenLabs)), adam (adam (ElevenLabs)), alice (alice (ElevenLabs)), bella (bella (ElevenLabs)), bill (bill (ElevenLabs)), brian (brian (ElevenLabs)), callum (callum (ElevenLabs)), charlie (charlie (ElevenLabs)), chris (chris (ElevenLabs)). Fetch the full list with GET /v1/data/ai/speech?expand=options.mp3 or wav. A model that only produces raw audio returns wav, and the row’s Format says so.Allowed values:
mp3 (MP3), wav (WAV).Example
Response fields
Each row indata is one audio file, keyed by these fields.