falAudio to audioComing soon

fal-ai/tada/3b/text-to-speech

Name: fal-ai/tada/3b/text-to-speech
Brand: fal

fal-ai/tada/3b/text-to-speech is an audio to audio tool from fal that runs in the background and returns audio. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.104 per 1,000 characters of prompt. The final charge comes from usage.

Limits

Runs: In the background
Returns: audio
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`audio_url` required	URL or file	—	URL of the reference audio file for voice cloning. The model will replicate this speaker's voice characteristics.
`transcript`	text		Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only.
`prompt` required	text	—	The text to synthesize into speech using the reference speaker's voice.
`language`	one of en, ar, ch, de, es, fr, it, ja, pl, pt	en	Language for text alignment. Use the appropriate code for non-English synthesis.
`num_extra_steps`	number (whole) 0 to 50	0	Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.
`temperature`	number … to 2	0.6	Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output.
`top_p`	number 0 to 1	0.9	Top-p (nucleus) sampling parameter for text generation.
`repetition_penalty`	number 1 to 2	1.1	Penalty applied to repeated tokens during generation.
`acoustic_cfg_scale`	number 0 to 10	1.6	Classifier-free guidance scale for acoustic feature generation.
`noise_temperature`	number 0 to 2	0.9	Temperature for noise in the flow matching diffusion process.
`num_inference_steps`	number (whole) 1 to 50	20	Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed.
`speed_up_factor`	number 0.5 to 2	1	Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down.
`output_format`	one of wav, mp3	wav	The format of the output audio file.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/tada/3b/text-to-speech",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/reference_audio.wav",
      "prompt": "The autumn leaves danced gracefully through the crisp morning air, painting the cobblestone streets with shades of amber and gold."
    }
  }'