EasyVoice text to speech is an MCP server published by ae.easyvoice, hosted at easyvoice.ae. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 7 tools, including text_to_speech, list_voices, get_usage, generate_long_form, create_podcast.
Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Convert text to a downloadable MP3 or WAV audio file with one of EasyVoice's 66 neural voices or your ready cloned voice_* ids (Pro or active 7-day pass; English). Returns a hosted audio URL (no inline audio). Per-call limit: 8,000 characters (4,000 for Arabic ar_* voices; 2,000 for clones) — text over the limit is automatically queued as a background job instead of erroring; poll get_job_status with the returned job_id for the result. Free keys can use the 12 free voices; Pro ($9.99/mo) unlocks the full catalog. A Pro account past the fair-use line is paced in characters a minute: a call may wait up to 20 seconds, and one that would wait longer returns a tool error saying when to retry.
| Parameter | Type | Description |
|---|---|---|
| text * | string | The text to speak. |
| speed | number | |
| voice | string | Catalog voice id or your ready cloned voice_* id. Call list_voices. |
| format | string | one of ["mp3","wav"] |
{
"name": "text_to_speech",
"title": "Text to Speech",
"description": "Convert text to a downloadable MP3 or WAV audio file with one of EasyVoice's 66 neural voices or your ready cloned voice_* ids (Pro or active 7-day pass; English). Returns a hosted audio URL (no inline audio). Per-call limit: 8,000 characters (4,000 for Arabic ar_* voices; 2,000 for clones) — text over the limit is automatically queued as a background job instead of erroring; poll get_job_status with the returned job_id for the result. Free keys can use the 12 free voices; Pro ($9.99/mo) unlocks the full catalog. A Pro account past the fair-use line is paced in characters a minute: a call may wait up to 20 seconds, and one that would wait longer returns a tool error saying when to retry.",
"inputSchema": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text to speak."
},
"speed": {
"type": "number",
"default": 1,
"maximum": 2,
"minimum": 0.5
},
"voice": {
"type": "string",
"default": "af_aoede",
"description": "Catalog voice id or your ready cloned voice_* id. Call list_voices."
},
"format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"default": "mp3"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"audio_url",
"voice",
"format",
"characters"
],
"properties": {
"voice": {
"type": "string"
},
"format": {
"type": "string"
},
"audio_url": {
"type": "string"
},
"characters": {
"type": "number"
},
"remaining_free_chars_today": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}List all 66 EasyVoice catalog voices (id, name, language, accent, gender, free/pro tier) plus this key's cloned voices. Call this before text_to_speech or create_podcast to pick voice ids.
No parameters.
{
"name": "list_voices",
"title": "List Voices",
"description": "List all 66 EasyVoice catalog voices (id, name, language, accent, gender, free/pro tier) plus this key's cloned voices. Call this before text_to_speech or create_podcast to pick voice ids.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"plan",
"voices",
"cloned"
],
"properties": {
"plan": {
"enum": [
"free",
"pro"
],
"type": "string"
},
"cloned": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name",
"status"
],
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false
}
},
"voices": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name",
"language",
"accent",
"gender",
"tier",
"available"
],
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"tier": {
"enum": [
"free",
"pro"
],
"type": "string"
},
"accent": {
"type": "string"
},
"gender": {
"type": "string"
},
"language": {
"type": "string"
},
"available": {
"type": "boolean"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}Check this API key's plan and usage. Free keys see today's used/remaining characters (shared 5,000/day pool, resets at midnight UTC), the 20 requests/minute rate limit and 2-concurrent cap. Pro keys are unlimited (fair use: 10M characters per rolling 30 days, then slowed to 30 requests and 10,000 characters a minute, 10 and 3,000 past 20M, on every surface -- never blocked or billed) at 60 requests/minute.
No parameters.
{
"name": "get_usage",
"title": "Get Usage",
"description": "Check this API key's plan and usage. Free keys see today's used/remaining characters (shared 5,000/day pool, resets at midnight UTC), the 20 requests/minute rate limit and 2-concurrent cap. Pro keys are unlimited (fair use: 10M characters per rolling 30 days, then slowed to 30 requests and 10,000 characters a minute, 10 and 3,000 past 20M, on every surface -- never blocked or billed) at 60 requests/minute.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"plan",
"rpm_limit"
],
"properties": {
"plan": {
"enum": [
"free",
"pro"
],
"type": "string"
},
"used": {
"type": "number"
},
"limit": {
"type": "number"
},
"reset_at": {
"type": "string"
},
"remaining": {
"type": "number"
},
"rpm_limit": {
"type": "number"
},
"unlimited": {
"type": "boolean"
},
"concurrency_limit": {
"type": "number"
},
"fair_use_chars_per_month": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}Generate long-form narration (up to 500,000 characters ≈ 9 hours of audio) as an async job. Requires a Pro subscription key. Kokoro narration voices only — Arabic (ar_*) and cloned (voice_*) voices are rejected by the Long-Form engine. For Arabic or cloned voices, use text_to_speech: scripts over its per-call cap queue as single background jobs, up to 50,000 characters, without chapter export. Returns a job id — poll get_job_status; parts render progressively and audio_url appears when completed.
| Parameter | Type | Description |
|---|---|---|
| tone | string | Tone preset. |
| input * | string | The full script, up to 500,000 characters. |
| pitch | number | Pitch shift in semitones (-4 to 4). |
| speed | number | |
| voice | string | Kokoro voice id — call list_voices for the catalog. |
| format | string | one of ["mp3","wav"] |
{
"name": "generate_long_form",
"title": "Generate Long-Form Narration",
"description": "Generate long-form narration (up to 500,000 characters ≈ 9 hours of audio) as an async job. Requires a Pro subscription key. Kokoro narration voices only — Arabic (ar_*) and cloned (voice_*) voices are rejected by the Long-Form engine. For Arabic or cloned voices, use text_to_speech: scripts over its per-call cap queue as single background jobs, up to 50,000 characters, without chapter export. Returns a job id — poll get_job_status; parts render progressively and audio_url appears when completed.",
"inputSchema": {
"type": "object",
"required": [
"input"
],
"properties": {
"tone": {
"enum": [
"neutral",
"warm",
"bright",
"bass"
],
"type": "string",
"default": "neutral",
"description": "Tone preset."
},
"input": {
"type": "string",
"description": "The full script, up to 500,000 characters."
},
"pitch": {
"type": "number",
"default": 0,
"maximum": 4,
"minimum": -4,
"description": "Pitch shift in semitones (-4 to 4)."
},
"speed": {
"type": "number",
"default": 1,
"maximum": 2,
"minimum": 0.5
},
"voice": {
"type": "string",
"default": "af_aoede",
"description": "Kokoro voice id — call list_voices for the catalog."
},
"format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"default": "mp3"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"job_id",
"status",
"input_chars"
],
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string"
},
"input_chars": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Create a two-host (A/B) podcast episode as an async job. Requires a Pro subscription key. Up to 60 segments; combined text up to 30,000 characters. voice_a and voice_b set the two speaker voices — your READY cloned voice_* ids are allowed. Returns a job id — poll get_job_status.
| Parameter | Type | Description |
|---|---|---|
| format | string | one of ["mp3","wav"] |
| voice_a * | string | Voice id for speaker A — catalog voice or one of your READY cloned voice_* ids. |
| voice_b * | string | Voice id for speaker B. |
| segments * | array | Alternating dialogue segments (max 60). |
{
"name": "create_podcast",
"title": "Create Podcast Episode",
"description": "Create a two-host (A/B) podcast episode as an async job. Requires a Pro subscription key. Up to 60 segments; combined text up to 30,000 characters. voice_a and voice_b set the two speaker voices — your READY cloned voice_* ids are allowed. Returns a job id — poll get_job_status.",
"inputSchema": {
"type": "object",
"required": [
"segments",
"voice_a",
"voice_b"
],
"properties": {
"format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"default": "mp3"
},
"voice_a": {
"type": "string",
"description": "Voice id for speaker A — catalog voice or one of your READY cloned voice_* ids."
},
"voice_b": {
"type": "string",
"description": "Voice id for speaker B."
},
"segments": {
"type": "array",
"items": {
"type": "object",
"required": [
"speaker",
"text"
],
"properties": {
"text": {
"type": "string"
},
"speaker": {
"enum": [
"A",
"B"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 60,
"minItems": 1,
"description": "Alternating dialogue segments (max 60)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"job_id",
"status"
],
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Enroll a custom cloned voice from an audio sample (async). Requires a Pro or active 7-day pass key. Provide exactly one of audio_base64 or audio_url (https). Sample limits: 10 MB max upload; wav, mp3 or m4a; a 10–30 second clean single-speaker recording (enrollment rejects clips shorter than 10 or longer than 30 seconds; trim longer recordings first). Account limits: maximum 3 cloned voices, 5 enrollments per day. Returns a voice_id with status "enrolling" — check list_voices until its status is "ready" (there is no job to poll), then use it in text_to_speech (Pro or active 7-day pass), create_podcast (Pro key), or POST /api/v1/audio/speech (REST, same key).
| Parameter | Type | Description |
|---|---|---|
| name * | string | Display name for the cloned voice. |
| consent * | boolean | Required attestation: you confirm you have the recording rights to this audio sample. The server rejects anything but an explicit true. |
| audio_url | string | https URL to the audio sample — fetched server-side, same 10 MB bound. |
| mime_type | string | Sample MIME type — wav, mp3 and m4a are accepted (the server enforces the exact allowlist). |
| audio_base64 | string | Base64-encoded audio sample (10 MB max decoded). |
{
"name": "clone_voice",
"title": "Clone a Voice",
"description": "Enroll a custom cloned voice from an audio sample (async). Requires a Pro or active 7-day pass key. Provide exactly one of audio_base64 or audio_url (https). Sample limits: 10 MB max upload; wav, mp3 or m4a; a 10–30 second clean single-speaker recording (enrollment rejects clips shorter than 10 or longer than 30 seconds; trim longer recordings first). Account limits: maximum 3 cloned voices, 5 enrollments per day. Returns a voice_id with status \"enrolling\" — check list_voices until its status is \"ready\" (there is no job to poll), then use it in text_to_speech (Pro or active 7-day pass), create_podcast (Pro key), or POST /api/v1/audio/speech (REST, same key).",
"inputSchema": {
"type": "object",
"oneOf": [
{
"required": [
"audio_base64"
]
},
{
"required": [
"audio_url"
]
}
],
"required": [
"name",
"consent"
],
"properties": {
"name": {
"type": "string",
"description": "Display name for the cloned voice."
},
"consent": {
"type": "boolean",
"const": true,
"description": "Required attestation: you confirm you have the recording rights to this audio sample. The server rejects anything but an explicit true."
},
"audio_url": {
"type": "string",
"description": "https URL to the audio sample — fetched server-side, same 10 MB bound."
},
"mime_type": {
"type": "string",
"default": "audio/wav",
"description": "Sample MIME type — wav, mp3 and m4a are accepted (the server enforces the exact allowlist)."
},
"audio_base64": {
"type": "string",
"description": "Base64-encoded audio sample (10 MB max decoded)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"voice_id",
"status"
],
"properties": {
"status": {
"type": "string"
},
"voice_id": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Check the status of a long-form, podcast or tts job owned by this key. Returns status plus audio URL(s) when completed. Audio links are not guaranteed to persist — download promptly.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string | Job id returned by an async tool. |
{
"name": "get_job_status",
"title": "Get Job Status",
"description": "Check the status of a long-form, podcast or tts job owned by this key. Returns status plus audio URL(s) when completed. Audio links are not guaranteed to persist — download promptly.",
"inputSchema": {
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"description": "Job id returned by an async tool."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"id",
"status"
],
"properties": {
"id": {
"type": "string"
},
"status": {
"type": "string"
},
"audio_url": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true
}
}EasyVoice is a hosted text-to-speech service. Free API keys can use the 12 free voices at 20 requests/minute, 2 concurrent requests, and a shared 5,000 characters/day pool; Pro ($9.99/mo flat) unlocks all 66 voices and removes the daily limit (fair use: 10M characters per rolling 30 days; past it the account is paced to 30 requests and 10,000 characters a minute, 10 requests and 3,000 characters a minute past 20M, on every surface including the studio -- never blocked or billed; a wait over 20 seconds comes back as a tool error saying when to retry, and jobs start when the account's character budget allows). Call list_voices first to pick a voice id. text_to_speech accepts up to 8,000 characters per call (4,000 for Arabic ar_* voices; 2,000 for your ready clones). Long-form scripts (generate_long_form) and podcast episodes (create_podcast) are Pro features — they run asynchronously: submit, then poll get_job_status. Voice cloning (clone_voice) works with Pro or an active 7-day pass: it replies at once with a voice_id in status "enrolling" and there is no job to poll — check list_voices until the status is "ready". Generated audio is kept for six months and then deleted — on the 1st of each month we remove the month that has passed six months. Download anything you want to keep; your generation history (the text and the settings) stays in your account. Generated audio links are not guaranteed to persist — download promptly.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.