ReplicateText to speechComing soon

inworld/realtime-tts-2

Name: inworld/realtime-tts-2
Brand: Replicate

inworld/realtime-tts-2 is a text to speech tool from Replicate 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

$0.0325 per 1,000 characters of text.

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
`text` required	text	—	The text to convert to speech. Maximum 2,000 characters. Supports natural-language steering with bracketed instructions placed before the text they apply to (e.g. `[say excitedly]`, `[whisper in a hushed style]`, `[say sadly with deliberate pauses in a low voice]`). Inline non-verbal tags are also supported (e.g. `[laugh]`, `[sigh]`, `[breathe]`, `[clear throat]`, `[cough]`, `[yawn]`). SSML break tags work for pauses (e.g. `<break time="1s" />`). Capitalize words for emphasis (e.g. `I told you NOT to do that`).
`language`	JSON	auto	Language of the input text. Use 'auto' to let the model detect the language. Supported production languages: English (en), Chinese (zh), Japanese (ja), Korean (ko), Russian (ru), Italian (it), Spanish (es), Portuguese (pt), French (fr), German (de), Polish (pl), Dutch (nl), Hindi (hi), Hebrew (he), Arabic (ar).
`voice_id`	text	Ashley	The voice to use. Use a preset voice name (e.g. 'Ashley', 'Dennis', 'Alex', 'Darlene') or a custom cloned voice ID.
`sample_rate`	JSON	48000	Audio sample rate in Hz.
`temperature`	number 0 to 2	0	Controls randomness when generating audio. Higher values produce more expressive results, lower values are more deterministic. Set to 0 to use the model default (1.1).
`audio_format`	JSON	mp3	Output audio format.
`speaking_rate`	number 0 to 1.5	0	Speaking speed multiplier. Set to 0 for normal speed (1.0).
`text_normalization`	JSON	auto	Controls whether numbers, dates, and abbreviations are expanded before synthesis. 'auto' lets the model decide, 'on' always normalizes, 'off' reads text as-is.

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": "replicate",
    "model": "inworld/realtime-tts-2",
    "input": {
      "text": "<text>"
    }
  }'