Core Speech Analysis

Synthesize speech via ElevenLabs (model: eleven_multilingual_v2) and return per-character timing alongside the audio.…

post/api/text-to-speech/generate-with-timing

Request

  • Base URL: https://platform.vocametrix.com
  • URL: https://platform.vocametrix.com/api/text-to-speech/generate-with-timing
  • Auth: API key in header X-API-Key

Request body

textstring required

Text to synthesize (1–2500 characters). REQUIRED.

isSSMLboolean

Boolean (optional, default false). Currently accepted but not applied to the request body — flag is reserved for future SSML support.

Response

Successful response

successboolean

Boolean — true on a successful synthesis

audio_base64string byte

Base64-encoded MP3 audio (ElevenLabs default format)

alignmentobject

Object with arrays of equal length: { characters: string[], character_start_times_seconds: number[], character_end_times_seconds: number[] }. Each i-th entry gives the start/end time in seconds of the i-th character of the synthesized audio.

normalized_alignmentstring

Same shape as alignment, but computed against the post-text-normalization sequence (numbers expanded, abbreviations expanded, etc.) — use this when your highlighter must follow what was actually pronounced, not the literal input text.

Changes

No recorded changes to this operation across all 1 revision of this API.