Skip to main content
curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/webm;codecs=opus' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --output output.webm \
  --fail \
  --data '{
  "text": "Hello from Rime!",
  "modelId": "arcana",
  "speaker": "astra",
  "lang": "en",
  "samplingRate": 24000
}'

Documentation Index

Fetch the complete documentation index at: https://docs.rime.ai/llms.txt

Use this file to discover all available pages before exploring further.

The streaming endpoint returns audio bytes in the format specified by the Accept header.

​
Audio Formats

Set the Accept header to one of the following values:
FormatAccept HeaderNotes
Opus (WebM)audio/webm;codecs=opusRecommended. Opus offers excellent compression. WebM streams natively in browsers.
Opus (OGG)audio/ogg;codecs=opusOpus offers excellent compression. OGG container.
MP3audio/mpegLower compression rate than Opus. Highest compatibility across devices and players.
WAVaudio/wavUncompressed. RIFF WAVE header with 16-bit little-endian linear PCM samples. Streams natively in browsers.
PCMaudio/L16Headerless 16-bit little-endian linear PCM.
G.711 μ-lawaudio/PCMUHeaderless stream of audio bytes.

​
Deprecated aliases

Still accepted for backwards compatibility; new code should use the RFC types above.
DeprecatedUse instead
audio/mp3audio/mpeg
audio/pcmaudio/L16
audio/x-mulawaudio/PCMU

​
Variable Parameters

​
speaker
string
required
Must be one of the flagship Arcana voices listed in our documentation.
​
text
string
required
The text you’d like spoken. Unlimited via API. Character limit per request is 3,000 in the dashboard UI.
​
modelId
string
Choose arcana for Rime’s most realistic conversational voices.
​
lang
string
default:"en"
If provided, the language must match the language spoken by the provided speaker. This can be checked in our voices documentation.
​
samplingRate
number
default:"24000"
The sampling rate (Hz).
​
timeScaleFactor
number
default:"1.0"
The time scaling factor.A value above 1.0 slows down the audio, a value below 1.0 speeds up the audio.
curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/webm;codecs=opus' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --output output.webm \
  --fail \
  --data '{
  "text": "Hello from Rime!",
  "modelId": "arcana",
  "speaker": "astra",
  "lang": "en",
  "samplingRate": 24000
}'