Word timestamps

This endpoint streams NDJSON — one JSON object per line — instead of raw PCM. Two kinds of line arrive:

The audio is the same PCM16 the streaming endpoint returns — it is simply base64-encoded and split across the audio_base64 lines instead of being sent as a raw byte stream.

To rebuild the clip: base64-decode each audio_base64 value and concatenate the bytes in the order the lines arrive. The result is headerless PCM — the same bytes the streaming endpoint would have given you. Most players need a container, so prepend a 44-byte WAV header (using your sample_rate, 1 channel, 16 bits) before writing a .wav file, or feed the samples straight into a Web Audio buffer.

Requires API key authentication via the x-api-key header. Single voice only — the speakers array supported by Synthesize is not accepted here.

Path parameters

Request body — Content-Type: application/json

The examples use the faseeh-v1-preview model with the ar-najdi-male-2 voice, and rebuild both the audio and the word list.

Status code: 200 OK. The body is a newline-delimited JSON stream.

A complete response looks like this — audio lines first, then the alignment lines. Every line carries all four keys, with null where a field does not apply:

A short clip like مرحبا بك في فصيح at 48 kHz comes back as roughly a dozen audio lines followed by the two alignment lines. Read to the end of the stream: closing early loses the timings entirely.

Line fields

Alongside the three timing arrays, each alignment object carries quality flags:

For highlighting, the practical rule is: bail out if aligned is false, and skip any word whose characters are all unanchored — its timing is a guess, and highlighting it will look wrong against the audio.

Both alignment objects share the same shape — three parallel arrays of equal length:

If your text contains a break tag, it stays in alignment exactly as you wrote it, with timings spanning the silence it produces — so offsets still line up with your string. It is not present in normalized_alignment, which describes the spoken form only. When grouping into words, treat the whole tag as one unit: splitting on whitespace alone tears it into <break and time="1s"/>.

Concatenating alignment.characters reproduces your input string exactly, so index i in those arrays is index i in your text — that is what makes it safe to map timings back onto your own string.

Timings are per character, not per word — there is no word array. Derive words by walking the arrays and breaking on whitespace: a word's start is its first character's start time, its end is its last character's end time. The Python example above does exactly this.

Errors come back as JSON with an errorCode and errorMessage.

Priced exactly like a standard synthesis request — from the text length and the model cost per character. Timestamps add no extra charge. The generation appears in your history the same way a streaming request does.