Streaming HTTP

Mist v3 streaming HTTP endpoint: low-latency TTS with the updated Mist engine.

cURL

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": "mistv3",
  "speaker": "cove",
  "lang": "en",
  "samplingRate": 24000
}'

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:

Format	Accept Header	Notes
Opus (WebM)	audio/webm;codecs=opus	Recommended. Opus offers excellent compression. WebM streams natively in browsers.
Opus (OGG)	audio/ogg;codecs=opus	Opus offers excellent compression. OGG container.
MP3	audio/mpeg	Lower compression rate than Opus. Highest compatibility across devices and players.
WAV	audio/wav	Uncompressed. RIFF WAVE header with 16-bit little-endian linear PCM samples. Streams natively in browsers.
PCM	audio/L16	Headerless 16-bit little-endian linear PCM.
G.711 μ-law	audio/PCMU	Headerless stream of audio bytes.

Deprecated aliases

Still accepted for backwards compatibility; new code should use the RFC types above.

Deprecated	Use instead
audio/mp3	audio/mpeg
audio/pcm	audio/L16
audio/x-mulaw	audio/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 mistv3.

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.

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.

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. Learn more about custom pauses.

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 “0.5, 3” to make “slow” slower and “fast” faster.

cURL

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": "mistv3",
  "speaker": "cove",
  "lang": "en",
  "samplingRate": 24000
}'