Skip to main content
curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/mpeg' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --output output.mp3 \
  --fail \
  --data '{
  "text": "Hello from Rime!",
  "modelId": "mistv2",
  "speaker": "astra",
  "lang": "eng",
  "samplingRate": 22050,
  "speedAlpha": 1.0
}'

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 HeaderDefault Sampling RateNotes
MP3audio/mpeg22050
PCMaudio/L1616000Headerless 16-bit little-endian linear PCM.
G.711 μ-lawaudio/PCMU8000Headerless 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 voices listed in our documentation.
​
text
string
required
The text you’d like spoken. Character limit per request is 500 via the API and 1,000 in the dashboard UI.
​
modelId
string
Set to mistv2.
​
lang
string
default:"eng"
If provided, the language must match the language spoken by the provided speaker. This can be checked in our voices documentation.
​
pauseBetweenBrackets
bool
default:"false"
When set to true, adds pauses between words enclosed in angle brackets. The number inside the brackets specifies the pause duration in milliseconds.
Example: “Hi. <200> I’d love to have a conversation with you.” adds a 200ms pause between the first and second sentences.
​
phonemizeBetweenBrackets
bool
default:"false"
When set to true, you can specify the phonemes for a word enclosed in curly brackets.
Example: “{h’El.o} World” will pronounce “Hello” as expected. Learn more about custom pronunciation.
​
inlineSpeedAlpha
string
Comma-separated list of speed values applied to words in square brackets. Values < 1.0 speed up speech, > 1.0 slow it down. Example: “This is [slow] and [fast]”, use “3, 0.5” to make “slow” slower and “fast” faster.
​
samplingRate
int
The value, if provided, must be between 4000 and 44100. Default depends on format (see table above).
​
speedAlpha
float
default:"1.0"
Adjusts the speed of speech. Lower than 1.0 is faster and higher than 1.0 is slower.Note: this is the legacy Mist v2 convention. Newer models (Coda, Arcana, Mist v3) invert it — for those, higher than 1.0 is faster.
​
noTextNormalization
bool
default:"false"
mist/mistv2 only. Skips text normalization of the input text prior to synthesizing audio. This will reduce latency at the cost of some possible mispronunciation of digits and abbreviations.
​
saveOovs
bool
default:"false"
mist/mistv2 only. If set to true, Rime shall save any currently OOV (out-of-vocabulary) words encountered in text, and save them for the User or Team to review on the Speech QA dashboard. Note: It may take up to 15 minutes for OOV words to appear on your dashboard.
curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/mpeg' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --output output.mp3 \
  --fail \
  --data '{
  "text": "Hello from Rime!",
  "modelId": "mistv2",
  "speaker": "astra",
  "lang": "eng",
  "samplingRate": 22050,
  "speedAlpha": 1.0
}'