GET
/v1/schemas/fal/audio/fal-ai%2Ftada%2F3b%2Ftext-to-speech
Accept:
Request body
13 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The text to synthesize into speech using the reference speaker's voice. | |
| audio_url* | string | URL of the reference audio file for voice cloning. The model will replicate this speaker's voice characteristics. | |
| language | enum | Language for text alignment. Use the appropriate code for non-English synthesis. | en | ar | ch | de | es | fr · +4 more · default: "en" |
| noise_temperature | number | Temperature for noise in the flow matching diffusion process. | 0 ≤ n ≤ 2 · default: 0.9 |
| temperature | number | Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output. | 0 < n ≤ 2 · default: 0.6 |
| top_p | number | Top-p (nucleus) sampling parameter for text generation. | 0 ≤ n ≤ 1 · default: 0.9 |
| repetition_penalty | number | Penalty applied to repeated tokens during generation. | 1 ≤ n ≤ 2 · default: 1.1 |
| speed_up_factor | number | Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down. | 0.5 ≤ n ≤ 2 · default: 1 |
| output_format | enum | The format of the output audio file. | wav | mp3 · default: "wav" |
| acoustic_cfg_scale | number | Classifier-free guidance scale for acoustic feature generation. | 0 ≤ n ≤ 10 · default: 1.6 |
| num_inference_steps | integer | Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed. | 1 ≤ n ≤ 50 · default: 20 |
| num_extra_steps | integer | Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence. | 0 ≤ n ≤ 50 · default: 0 |
| transcript | string | Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only. | default: "" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/tada/3b/text-to-speech","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}