Skip to main content
Speed controls use different parameters and value directions by model. Use this table before changing a request:

​
Adjusting the overall speed

​
Coda and Mist v3

Use the timeScaleFactor parameter. A value above 1.0 slows the audio, and a value below 1.0 speeds it up. Values outside 0.4 to 2.5 are clamped to the nearest limit.
Coda and Mist v3 also accept speedAlpha, but it works in the opposite direction from timeScaleFactor (higher than 1.0 is faster, lower is slower). Use timeScaleFactor for these models. If a request sends both, timeScaleFactor is used.
timeScaleFactor works over both HTTP and WebSocket endpoints. For Coda WebSocket v1, set start.audioParameters.timeScaleFactor. For the legacy /ws, /ws2, and /ws3 endpoints, pass it as a query parameter when you open the connection.

​
Adjusting the speed of individual words

Per-word speed adjustment with inlineSpeedAlpha works on Mist v3 over HTTP. Coda doesn’t support it, and the WebSocket endpoints don’t read it.
To adjust the speed of individual words or phrases on Mist v3, use the inlineSpeedAlpha parameter. It takes a comma-separated list of speed values applied to words in square brackets. On Mist v3, values < 1.0 speed up speech and values > 1.0 slow it down.
On Mist v3, inlineSpeedAlpha and speedAlpha go in opposite directions. speedAlpha is higher-is-faster, like Coda, while inlineSpeedAlpha is lower-is-faster. Don’t infer one from the other.
For example: “This sentence is [really] [fast]” with inlineSpeedAlpha “0.5, 3” will make “really” fast and “fast” slow on Mist v3.

​
Evaluate the result

Start near 1.0 and evaluate representative audio before increasing the adjustment. Large changes can reduce naturalness and clarity.