Skip to main content
The Rime API authenticates every request with a bearer token in the Authorization header: Authorization: Bearer YOUR_API_KEY. See API authentication for how to create a key. The endpoint streams audio in the format you name in the Accept header. Always set it, because a request without Accept returns 400. A wildcard (*/*) returns WAV, and so does a type the API can’t stream.

Audio formats

Set the Accept header to one of the following values:

Deprecated aliases

The API still accepts these for backward compatibility. Use the RFC types above in new code.

Variable parameters

string
A Coda voice from the voice catalog. If you leave it out, Coda picks a voice at random for each request, which helps when you try out a language. Set it when every request needs the same voice.
string
required
The text you’d like spoken. The API accepts up to 1,000 characters per request.
string
default:"en"
If provided, the language must match the language spoken by the provided speaker. Pass a BCP 47 language tag:The 3-letter ISO 639-2 codes that older integrations send (eng, spa, fra, por, ger, jpn, ara, hin, ita, nld) remain accepted, and will stay accepted.See the voices documentation for which speakers support each language.
object[]
Pronunciations for words and phrases in text. Each entry is an object with a spelling and its X-SAMPA pronunciation, and a request can carry up to 500 entries. Coda accepts a lexicon when lang is en, de, es, fr, it, or pt, and returns 400 for other languages. See Phoneme control for the format and examples.
number
default:"24000"
The sampling rate (Hz).
number
default:"1.0"
The time scaling factor. Accepted range is 0.4 to 2.5. Values outside this range are clamped without an error.Values above 1.0 slow the audio down, and values below 1.0 speed it up.