Speechify

Speechify is a text-to-speech platform whose Speechify Voice API (also surfaced through Speechify Studio) synthesizes lifelike speech in 30+ languages from plain text or SSML. The REST API at https://api.sws.speechify.com offers non-streaming and streaming text-to-speech, a voice catalog, and instant voice cloning, authenticated with a Bearer API key.

4 APIs 0 Features

AIText to SpeechVoiceSpeech SynthesisVoice Cloning

APIs

Speechify Text-to-Speech API

Synthesizes lifelike speech from plain text or SSML via POST /v1/audio/speech, returning base64-encoded audio (wav, mp3, ogg, aac, or pcm) plus speech marks for word-level timin...

Speechify Streaming TTS API

Streams synthesized audio as a chunked HTTP response from POST /v1/audio/stream for sub-300ms time-to-first-byte playback, with Accept values of audio/mpeg, audio/ogg, audio/aac...

Speechify Voices API

Lists the available voices via GET /v1/voices, including 1,000+ pre-set Speechify voices and any personal cloned voices, each with id, gender, locale, and tags for selection by ...

Speechify Voice Cloning API

Creates an instant personal voice clone from a 10-30 second audio sample via multipart POST /v1/voices with explicit consent (full name and email), and removes cloned voices via...

Collections

Speechify Voice API

OPEN

Pricing Plans

Speechify Plans Pricing

3 plans

PLANS

Rate Limits

Speechify Rate Limits

4 limits

RATE LIMITS

FinOps

Speechify Finops

FINOPS

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Speechify Voice API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Audio
    type: folder
  items:
  - info:
      name: Convert text to speech
      type: http
    http:
      method: POST
      url: https://api.sws.speechify.com/v1/audio/speech
      body:
        type: json
        data: "{\n  \"input\": \"Hello from Speechify!\",\n  \"voice_id\": \"<string>\",\n  \"language\": \"en-US\",\n  \"\
          model\": \"simba-english\",\n  \"audio_format\": \"mp3\"\n}"
    docs: Synthesizes speech and returns JSON with base64 audio_data, audio_format, billable_characters_count, and speech_marks.
  - info:
      name: Stream text to speech
      type: http
    http:
      method: POST
      url: https://api.sws.speechify.com/v1/audio/stream
      headers:
      - name: Accept
        value: audio/mpeg
      body:
        type: json
        data: "{\n  \"input\": \"Hello from Speechify!\",\n  \"voice_id\": \"<string>\",\n  \"language\": \"en-US\",\n  \"\
          model\": \"simba-english\"\n}"
    docs: Streams synthesized audio as a chunked HTTP response. WAV is not available for streaming.
- info:
    name: Voices
    type: folder
  items:
  - info:
      name: List voices
      type: http
    http:
      method: GET
      url: https://api.sws.speechify.com/v1/voices
    docs: Returns available pre-set and personal voices.
  - info:
      name: Create a voice clone
      type: http
    http:
      method: POST
      url: https://api.sws.speechify.com/v1/voices
      body:
        type: multipart-form
        data: []
    docs: Creates an instant personal voice clone from a 10-30 second audio sample with explicit consent (fullName and email).
  - info:
      name: Delete a voice
      type: http
    http:
      method: DELETE
      url: https://api.sws.speechify.com/v1/voices/{id}
    docs: Deletes a personal (cloned) voice by id.