API Reference
API Reference / Endpoints

Speech endpoints

/v1/speech/*

TTS, STT, dialogue, dubbing, voice isolation, and related speech helpers.

What this section covers

Endpoint-level reference for the current /v1/speech/* surface.

Speech routes mix JSON and multipart inputs, so the biggest integration mistake is usually the wrong request format rather than the wrong path.

Streaming text to speech returns audio bytes progressively. Other speech workflows may be async or mixed; streaming speech to text remains reserved.

Start here

Recommended starting point

Use POST/v1/speech/text-to-speech for standard async TTS.

Recommended starting point

Use POST/v1/speech/speech-to-text with multipart audio for transcription.

Recommended starting point

Use GET/v1/speech/voices before building a picker UI.

Synthesis

Turn text into voice or multi-speaker audio.

POSTAsync
View reference

Text to speech

/v1/speech/text-to-speech

Generate speech asynchronously from text.

Poll response
After the POST returns request_id, poll the response endpoint.GET/v1/requests/:requestId
audio:generatejsonConsumes 1 API call
POSTStreaming audio
View reference

Streaming text to speech

/v1/speech/text-to-speech/stream

Receive speech audio progressively from complete input text.

audio:generatejsonConsumes 1 API call
GETSync
View reference

List voices

/v1/speech/voices

Fetch the speech voice catalog for picker UIs and integrations.

audio:generateNo bodyFree
POSTAsync
View reference

Text to dialog

/v1/speech/text-to-dialog

Generate multi-speaker dialogue from structured line inputs.

Poll response
After the POST returns request_id, poll the response endpoint.GET/v1/requests/:requestId
audio:generatejsonConsumes 1 API call

Transcription and cleanup

Transcribe files or isolate clean voice audio.

POSTSync or async
View reference

Speech to text

/v1/speech/speech-to-text

Transcribe uploaded audio. Returns 200 for short jobs or 202 for longer work.

Poll response
If this returns 202 with a request_id, poll the response endpoint.GET/v1/requests/:requestId
audio:generatemultipartBillable when generation starts
POSTReserved
View reference

Streaming speech to text

/v1/speech/speech-to-text/stream

Reserved streaming STT surface.

audio:generateNo bodyReserved
POSTAsync
View reference

Voice isolator

/v1/speech/voice-isolator

Isolate speech from a mixed audio file.

Poll response
After the POST returns request_id, poll the response endpoint.GET/v1/requests/:requestId
audio:generatemultipartConsumes 1 API call
GETSync
View reference

Speech status

/v1/speech/status/:requestId

Read a speech-specific status payload for a prior speech request.

analytics:readNo bodyFree

Localization and advanced flows

Dubbing and future voice transformation surfaces.

POSTAsync
View reference

Dubbing

/v1/speech/dubbing

Create a dubbing job from uploaded media or a source URL.

Poll response
After the POST returns request_id, poll the response endpoint.GET/v1/requests/:requestId
audio:generatemultipartConsumes 1 API call
GETSync
View reference

Fetch dubbing transcript

/v1/speech/dubbing/:dubbingId/transcript

Fetch the transcript for a dubbing job when available.

audio:generateNo bodyFree
POSTReserved
View reference

Voice changer

/v1/speech/voice-changer

Reserved speech surface that is not available in API v1.

audio:generateNo bodyReserved
Was this page helpful?
Previous
Sound Effects endpointsNext