MCP tool reference · #552 of 563 by publishers

text_to_speech

Exposed by 10 servers from 8 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 100% of them take a text parameter; the most-starred is Sats4AI - Bitcoin-Powered AI Tools (2 stars).

text_to_speech(text: string, voice?: string, format?: string, speed?: number, lang?: string, …)

Parameters

share = % of the 10 servers whose schema has it · required = % of those that mark it required
ParameterTypeShareRequiredUsual description
textstring100%70%Text to speak, up to 2,000 characters
voicestring80%12.5%Voice name. English: amalthea, andromeda, apollo, arcas, aries, asteria, athena, atlas, aurora, callista, cora, cordelia, delia, draco, electra, harmonia, helen
formatstring60%0%Audio format: mp3 (default), wav, pcm (raw 16-bit little-endian mono), ulaw or alaw (8 kHz telephony, e.g. Twilio), opus (Ogg) or flac. opus and flac only for t
speednumber50%0%Optional speaking speed (0.5–2).
langstring40%0%Language: en or es (Aura-2 MP3, many voices); fr, zh, ja and ko are retired (MeloTTS was removed from Workers AI, 20 Nov 2026); default en
languagestring30%0%Language of the text when no voice is given, like 'German' or 'pt-BR'.
pronunciationsstring30%0%How to say words: JSON {"Nginx":"engine x","GIF":"jif"} or Nginx=engine x, GIF=jif (up to 50, whole words, any case)
sample_ratestring | number | boolean30%0%Sample rate in Hz for wav and pcm (8000, 16000, 24000 default, 32000, 48000) or ulaw/alaw (8000 default, 16000)
wait_secondsinteger20%0%How long to wait for a result, 0–55 seconds (default 30).
idempotency_keystring10%0%Optional caller correlation key. Billing is handled by mcp-credit-gateway.
include_audioboolean10%0%Also return the audio bytes in the result (large). Default false; the link is enough for most clients.
job_idstring10%0%Existing Qwen-TTS job id. Polling never creates a new upstream job.

Source: the input schema each server returns for text_to_speech, aggregated over the 10 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.

Servers with text_to_speech

10 of 10 · 8 publishers · 10 answering live · most-starred first, 3 per publisher
#Server★Live
1Sats4AI - Bitcoin-Powered AI Toolscnghockey · Communication2yes
2Agent Data Tools: Speech to text and text to speechnutshell2000 · Media & Creative1yes
3Agent Data Tools: Full list (every tool as its own definition)nutshell2000 · Documents & Knowledge1yes
4Agent Data Tools: AInutshell2000 · AI & Agents1yes
5Embeddings, Rerank & Speech-to-Text (Tanod)tanod-labs · AI & Agents1yes
6AIPayGendamien829 · Search & Web—yes
7ImgKits MCPyichong1 · Media & Creative—yes
8Finekot APIdenyskot1986 · Media & Creative—yes
9TTSForFreecalmnguyen · Media & Creative—yes
10FreeTTSfreetts · Media & Creative—yes

Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.