fal.ai·Text to speech

MiniMax Speech-02 HD

/fal-ai/minimax/speech-02-hdasync$0.15 / 1,000 characters

Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per 1,000 characters.

Charged per 1,000 characters produced; a call that produces nothing is charged one unit.

Input

output_formatstring
Format of the output content (non-streaming only) (default "hex")
url, hex
voice_settingobject
voice_setting
language_boostany
Enhance recognition of specified languages and dialects
audio_settingobject
audio_setting
pronunciation_dictany
Custom pronunciation dictionary for text replacement
textstringrequired
Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)

Field	Type	Required	Description
output_format	string (url, hex)	—	Format of the output content (non-streaming only) (default "hex")
voice_setting	object	—	voice_setting
language_boost	any	—	Enhance recognition of specified languages and dialects
audio_setting	object	—	audio_setting
pronunciation_dict	any	—	Custom pronunciation dictionary for text replacement
text	string	yes	Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/minimax/speech-02-hd","input":{"text":"Hello from Sooma."}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.