✛ Media

VoiceOver TTS

Send English text and get an MP3 at a steady loudness with the start and end of every word. Up to 2,000 characters are spoken in the same call, usually within a second; up to 20,000 characters are queued and split for you. Pauses are written as <break time="500ms"/>, and say_as fixes names the voice gets wrong. Words the voice cannot pronounce are skipped.

Queue speech for a text. Charged per 100 characters spoken, rounded up; pauses are free.

POST/v1/voiceover/speak
Try it ↓

Answers 202 with a job_id. Poll GET /v1/jobs/{id} (free) or pass callback_url. How long jobs work.

Price
$0.00012 per 100 characters · REST and MCP
RapidAPI
$0.00015 per 100 characters · listing at launch
Per call
up to 20,000 characters · at most $0.024
Returns
application/json
MCP tool
tts_pro_speak

Request body

FieldTypeDescription
textrequiredstringEnglish text. <break time="500ms"/> or <break time="1.5s"/> adds a pause, up to 5 s.
voiceaf_heart af_bella af_nicole am_michael am_fenrir am_puck bf_emma bf_isabella bm_george bm_fableaf/am are American, bf/bm British; f and m are the voice's pitch.
speednumber0.5 to 2. Normal speed is 1.
say_asobjectWhole words to say differently, as {"SQL": "sequel"}. At most 100. Word timings show the replacement, and its characters are the ones charged.
callback_urlstringTold the job's id and status when it ends, signed with your webhook secret.
example
curl https://readymadeapi.com/v1/voiceover/speak \
  -H "Authorization: Bearer $READYMADE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome back. <break time=\"500ms\"/> Here is today'\''s update.",
    "voice": "af_heart"
  }'
What comes backAt once, from this call (202)
{
  "job_id": "01a1f553-94c4-730e-9222-464724610044",
  "status": "queued",
  "status_url": "/v1/jobs/01a1f553-94c4-730e-9222-464724610044",
  "result_url": "/v1/jobs/01a1f553-94c4-730e-9222-464724610044/result"
}
Later, from GET /v1/jobs/{id}, when the job is done
{
  "job_id": "01a1f553-94c4-730e-9222-464724610044",
  "status": "succeeded",
  "late": false,
  "deadline": "2026-11-20T19:40:57.921846Z",
  "completed_at": "2026-11-19T19:40:59.339674Z",
  "error": null,
  "result": {
    "words": [
      {
        "end": 0.775,
        "word": "Welcome",
        "start": 0.375
      },
      {
        "end": 1.375,
        "word": "back",
        "start": 0.775
      },
      {
        "end": 2.65,
        "word": "Here",
        "start": 2.425
      },
      {
        "end": 2.8,
        "word": "is",
        "start": 2.65
      },
      {
        "end": 3.175,
        "word": "today's",
        "start": 2.8
      },
      {
        "end": 3.9,
        "word": "update",
        "start": 3.175
      }
    ],
    "audio_mime": "audio/mpeg",
    "duration_s": 4.15,
    "audio_base64": "SUQzBAAAAAAAIlRTU0UAAAAOAAADTGF2ZjYyLjMuMTAwAAAAAAAAAAAAAAD/... (45116 characters)"
  }
}

Try it · $0.00012 per 100 characters, paid from your credit

No key yet? Get an API key · it works for every API.

Speak up to 2,000 characters and get the MP3 and word timings in the same call, usually within a second.

POST/v1/voiceover/instant
Try it ↓
Price
$0.00012 per 100 characters · REST and MCP
RapidAPI
$0.00015 per 100 characters · listing at launch
Per call
up to 2,000 characters · at most $0.0024
Returns
application/json
MCP tool
tts_pro_speak_now

Request body

FieldTypeDescription
textrequiredstringEnglish text. <break time="500ms"/> or <break time="1.5s"/> adds a pause, up to 5 s.
voiceaf_heart af_bella af_nicole am_michael am_fenrir am_puck bf_emma bf_isabella bm_george bm_fableaf/am are American, bf/bm British; f and m are the voice's pitch.
speednumber0.5 to 2. Normal speed is 1.
say_asobjectWhole words to say differently, as {"SQL": "sequel"}. At most 100. Word timings show the replacement, and its characters are the ones charged.
callback_urlstringTold the job's id and status when it ends, signed with your webhook secret.
example
curl https://readymadeapi.com/v1/voiceover/instant \
  -H "Authorization: Bearer $READYMADE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Your order has shipped and will arrive on Friday.",
    "voice": "af_heart"
  }'
What comes back
{
  "audio_base64": "SUQzBAAAAAAAIlRTU0UAAAAOAAADTGF2ZjYyLjMuMTAwAAAAAAAAAAAAAAD/... (34876 characters)",
  "audio_mime": "audio/mpeg",
  "duration_s": 3.175,
  "words": [
    {
      "word": "Your",
      "start": 0.275,
      "end": 0.425
    },
    {
      "word": "order",
      "start": 0.425,
      "end": 0.65
    },
    {
      "word": "has",
      "start": 0.65,
      "end": 0.863
    },
    {
      "word": "shipped",
      "start": 0.863,
      "end": 1.363
    },
    {
      "word": "and",
      "start": 1.363,
      "end": 1.5
    },
    {
      "word": "will",
      "start": 1.5,
      "end": 1.65
    },
    {
      "word": "arrive",
      "start": 1.65,
      "end": 2.013
    },
    {
      "word": "on",
      "start": 2.013,
      "end": 2.212
    },
    {
      "word": "Friday",
      "start": 2.212,
      "end": 2.9
    }
  ]
}

Try it · $0.00012 per 100 characters, paid from your credit

No key yet? Get an API key · it works for every API.

Use it from an agent

Every endpoint above is also an MCP tool. Add the server to Claude, Cursor or any MCP client and the tools appear with their prices; calls draw from the same credit.

Connect guide · OpenAPI 3.1 spec · llms.txt

mcp config
{
  "mcpServers": {
    "readymade": {
      "type": "http",
      "url": "https://readymadeapi.com/mcp",
      "headers": {
        "Authorization": "Bearer ${READYMADE_KEY}"
      }
    }
  }
}