fal.ai·Text to speech

ElevenLabs TTS Turbo v2.5

/fal-ai/elevenlabs/tts/turbo-v2.5async$0.1 / 1,000 characters

Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5. 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

language_codeany
Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.
voicestring
The voice to use for speech generation (default "Rachel")
apply_text_normalizationstring
This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. (default "auto")
auto, on, off
stylenumber
Style exaggeration (0-1) (default 0)
previous_textany
The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.
speednumber
Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. (default 1)
textstringrequired
The text to convert to speech
stabilitynumber
Voice stability (0-1) (default 0.5)
similarity_boostnumber
Similarity boost (0-1) (default 0.75)
next_textany
The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.
timestampsboolean
Whether to return timestamps for each word in the generated speech (default false)

Field	Type	Required	Description
language_code	any	—	Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.
voice	string	—	The voice to use for speech generation (default "Rachel")
apply_text_normalization	string (auto, on, off)	—	This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. (default "auto")
style	number	—	Style exaggeration (0-1) (default 0)
previous_text	any	—	The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.
speed	number	—	Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. (default 1)
text	string	yes	The text to convert to speech
stability	number	—	Voice stability (0-1) (default 0.5)
similarity_boost	number	—	Similarity boost (0-1) (default 0.75)
next_text	any	—	The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.
timestamps	boolean	—	Whether to return timestamps for each word in the generated speech (default false)

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/elevenlabs/tts/turbo-v2.5","input":{"text":"Hello from Sooma."}}'

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