Skip to content

ElevenLabs · fal.ai · Expressive text to speech

Eleven v4

ElevenLabs Eleven v4, expressive text to speech, served by fal.ai. Convert text into speech with Eleven v4 from ElevenLabs. Price: $0.08 per 1,000 characters of text, pro rata (at most 5,000 characters per request). Waits up to 40 s for the result; if the generation takes longer, the run stays RUNNING and returns a request_id; poll fal/status and fetch fal/result with model "elevenlabs/tts" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

$0.08 / unitfal.aiAudiofal/elevenlabs-tts-v4

Use this tool with your agent

Give this to your agent
Use my connected Agentik MCP server. I want to use the tool fal/elevenlabs-tts-v4 (ElevenLabs Eleven v4, expressive text to speech). Call inspect_tool with {"tool_id": "fal/elevenlabs-tts-v4"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/elevenlabs-tts-v4" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If it cannot run right now, use discover_tools to propose a similar tool.
Show the prompt

Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.

Parameters

NameTypeRequiredDescription
output_formatstringNoOutput format of the generated audio. Formatted as codec_sample_rate_bitrate. Options: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000.
apply_text_normalizationstringNoWhether to normalize text such as numbers and dates before generation. Options: auto, on, off.
textstringYesThe text to convert to speech. Supports audio tags such as [whispering] and IPA pronunciation enclosed in forward slashes.
timestampsbooleanNoWhether to return character-level timing information with the generated audio.
similarity_boostnumberNoHow closely the output follows the reference voice. Higher values increase similarity but may reduce naturalness.
language_codestringNoLanguage code (ISO 639-1) for speech generation and text normalization.
voicestringNoThe voice to use for speech generation
seedintegerNoSeed for best-effort reproducibility. Identical output is not guaranteed.
stabilitynumberNoVoice stability. Lower values allow more expressive delivery; higher values make delivery more consistent.

How your agent calls it

First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:

{
  "tool_id": "fal/elevenlabs-tts-v4",
  "input": {
    "text": "Hello from Agentik, this is a short health check."
  }
}

Price and billing

Price
$0.08 / unit
Model
Per unit
Detail
The provider’s price, with no markup. Billed for measured usage.
  • The provider’s price, 0% markup.
  • One prepaid balance for every provider; your agent sees the price before it runs.
  • Pay for measured usage; unused reservations are released.