Synthesize Speech
Speech Generation
Synthesize Speech
Generate speech audio from text.
POST
Synthesize Speech
Overview
Turns text into speech and streams the audio back as it renders.text and voice are the only required fields. You get 48 kHz PCM frames by default — ready to play or forward straight to a client. Set audio.container to wav for a file you can download and open.
Use a
BTTS_V3 or newer voice. expressiveness and stability are calibrated for
it, and 48 kHz is the rate it renders natively. BTTS_V2 voices synthesize, but the
controls are not tuned for them. Read x-model to see which model a voice resolved to.Pricing
Text-to-speech pricing scales with plan:
Some public-library voices carry an additional per-character creator fee. The exact charge for a request comes back in the
x-cost header.
Billing follows delivery. A synthesis that fails before any bytes are written is not charged, and a fully delivered request is charged for the whole text. If the connection drops mid-stream, you are charged for the characters whose audio already reached you.
Headers
string
required
Your API key.
Body Parameters
string
required
The text to speak. Maximum 5,000 characters.Insert a pause with
<|N|>, where N is 0.1 to 10.0 seconds: "Welcome to Bland. <|0.8|> How can I help?"string
required
Voice UUID. Names are not accepted — get a UUID from List Voices.
object
Output format. All fields optional.
object
How the voice performs. Both optional, both
0.0–1.0.Response
Audio in the encoding and container you asked for.raw+pcm_s16le→Content-Type: audio/pcmraw+mulaw→Content-Type: audio/basicwav(any encoding) →Content-Type: audio/wav
string
Unique ID for this request. Include it in support tickets.
string
The model that produced the audio, for example
btts-3. Set by the voice you chose.string
The voice UUID used.
string
Output sample rate in Hz.
string
Cost in USD, matching what was billed.
string
Milliseconds to the first audio byte. For
wav, the full render time.Errors
Every error returns the same shape, with a stable machine-readable code:Examples
Downloadable WAV file
cURL
Default (48 kHz PCM, raw)
cURL
Telephony (μ-law, 8 kHz)
cURL
Docs for agents: llms.txt