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| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| text | string | 100% | 70% | Text to speak, up to 2,000 characters |
| voice | string | 80% | 12.5% | Voice name. English: amalthea, andromeda, apollo, arcas, aries, asteria, athena, atlas, aurora, callista, cora, cordelia, delia, draco, electra, harmonia, helen |
| format | string | 60% | 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 |
| speed | number | 50% | 0% | Optional speaking speed (0.5–2). |
| lang | string | 40% | 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 |
| language | string | 30% | 0% | Language of the text when no voice is given, like 'German' or 'pt-BR'. |
| pronunciations | string | 30% | 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_rate | string | number | boolean | 30% | 0% | Sample rate in Hz for wav and pcm (8000, 16000, 24000 default, 32000, 48000) or ulaw/alaw (8000 default, 16000) |
| wait_seconds | integer | 20% | 0% | How long to wait for a result, 0–55 seconds (default 30). |
| idempotency_key | string | 10% | 0% | Optional caller correlation key. Billing is handled by mcp-credit-gateway. |
| include_audio | boolean | 10% | 0% | Also return the audio bytes in the result (large). Default false; the link is enough for most clients. |
| job_id | string | 10% | 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 | Publisher | Category | ★ | Live | How it describes text_to_speech |
|---|---|---|---|---|---|---|
| 1 | Sats4AI - Bitcoin-Powered AI Toolscnghockey · Communication | cnghockey | Communication | 2 | yes | Text-to-speech with 3 tiers: OmniVoice Global (602+ languages including Yoruba, Bengali, Cebuano, Twi, voice design, ~106 chars/sat — use 'language' parameter with ISO code), Inworld Premium (#1 ranked TTS ELO 1217, emotion control, 40+ languages, ~16 chars/sat), Minimax Studio (voice cloning from reference clip, 40+ languages, ~5 chars/sat). Adjustable speed (0.5-2.0x). Returns audio URL. Pay wit |
| 2 | Agent Data Tools: Speech to text and text to speechnutshell2000 · Media & Creative | nutshell2000 | Media & Creative | 1 | yes | Text to speech for a paragraph or a page: up to 2,000 characters as one MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2; fr, zh, ja and ko are retired with MeloTTS (Workers AI, 20 Nov 2026). Pick a voice by name or leave the default. Use for narration, article and summary read-outs, voice replies, IVR prompts and accessibility; for a sentence of up to 300 characters ai_speec |
| 3 | Agent Data Tools: Full list (every tool as its own definition)nutshell2000 · Documents & Knowledge | nutshell2000 | Documents & Knowledge | 1 | yes | Text to speech for a paragraph or a page: up to 2,000 characters as one MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2; fr, zh, ja and ko are retired with MeloTTS (Workers AI, 20 Nov 2026). Pick a voice by name or leave the default. Use for narration, article and summary read-outs, voice replies, IVR prompts and accessibility; for a sentence of up to 300 characters ai_speec |
| 4 | Agent Data Tools: AInutshell2000 · AI & Agents | nutshell2000 | AI & Agents | 1 | yes | Text to speech for a paragraph or a page: up to 2,000 characters as one MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2; fr, zh, ja and ko are retired with MeloTTS (Workers AI, 20 Nov 2026). Pick a voice by name or leave the default. Use for narration, article and summary read-outs, voice replies, IVR prompts and accessibility; for a sentence of up to 300 characters ai_speec |
| 5 | Embeddings, Rerank & Speech-to-Text (Tanod)tanod-labs · AI & Agents | tanod-labs | AI & Agents | 1 | yes | mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. For audio to text use transcribe_audio. Returns the text spoken as audio. Offline neural TTS (Kokoro-82M); the audio is a synthetic voice. At most 2,000 characters; 41 voices in 6 languages (the voice sets the language: write the text in it). Bad input is a 422, a busy or unavailable model a 503, a synthes |
| 6 | AIPayGendamien829 · Search & Web | damien829 | Search & Web | — | yes | Turn text into natural-sounding speech (WAV or MP3 audio) in English, Spanish, French, Chinese, Japanese or Korean. Returns the audio as a base64 data URL. Good for voice replies, narration and accessibility. Costs $0.006 per call. |
| 7 | ImgKits MCPyichong1 · Media & Creative | yichong1 | Media & Creative | — | yes | Synthesize speech from text via Qwen-TTS using a short `refer_audio` sample (http(s) URL). Pass `text` (<= 5000) + `refer_audio` (+ recommended `refer_audio_text`) to start, or `job_id` to poll. voiceId library voices are not exposed this wave. Cost: 2 credits per call. Compliance: Use only on material you own or are explicitly licensed/authorized to generate or remix. Do not generate or redistrib |
| 8 | Finekot APIdenyskot1986 · Media & Creative | denyskot1986 | Media & Creative | — | yes | Natural voice from text, 24 kHz. 21 voices: English US/UK, Spanish, French, Italian, Portuguese, Hindi, Japanese, Chinese. Output: MP3, OGG or WAV. Up to 5 000 chars per call; billed per started 1 000 chars. Cost €0.015 per 1 000 chars, charged to the API key in Authorization: Bearer. Parameters — text: string, up to 5 000 chars; voice: af_heart (default) | af_bella | am_adam | bf_emma | bm_george |
| 9 | TTSForFreecalmnguyen · Media & Creative | calmnguyen | Media & Creative | — | yes | Convert one text into one MP3 with one voice. Use for narration, voiceover scripts, articles, lessons, announcements or any audio whose length can follow the speech. Consumes credits (characters x voice rate). Returns job_id, status and audio_url when ready. |
| 10 | FreeTTSfreetts · Media & Creative | freetts | Media & Creative | — | yes | Convert text to spoken audio with a FreeTTS voice and return a download link to the MP3 (or WAV with a FreeTTS PRO key). Use it when the user wants text read aloud, narrated, or saved as an audio file. Without a FreeTTS key: standard voices, up to 2,000 characters a call, a short spoken "FreeTTS" tag at the end, file kept one hour. With a key: the account's plan (PRO: HD and Signature voices, no t |
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.