Skip to navigation

Stream Speech

Synthesize speech and stream the audio back as it is generated, for low-latency playback. Set output_format in the body for explicit codec/sample-rate/bitrate control (e.g. pcm_16000 or ulaw_8000 for telephony), or fall back to the Accept header for the container; the response is raw audio bytes (HTTP chunked). For Base64-encoded audio with speech-mark metadata in a single JSON response, use POST /v1/audio/speech.

Authentication

AuthorizationBearer

Enter your API key with the Bearer prefix, e.g. 'Bearer sk_...'.

Headers

Speechify-VersionstringOptional
AcceptenumOptional

Selects the audio container/codec for the streamed response when output_format is not set in the request body. The response Content-Type echoes this value, except audio/pcm returns audio/L16 with rate and channels parameters (raw 16-bit linear PCM, 24 kHz mono, little-endian). For explicit sample-rate/bitrate control (e.g. pcm_16000, ulaw_8000), set output_format in the body instead; it takes precedence over this header.

Allowed values:

Request

This endpoint expects an object.
inputstringRequired<=20000 characters

Plain text or SSML to be synthesized to speech. Refer to https://docs.speechify.ai/docs/api-limits for the input size limits. Emotion, Pitch and Speed Rate are configured in the ssml input, please refer to the ssml documentation for more information: https://docs.speechify.ai/docs/ssml#prosody

voice_idstringRequired

Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices

languagestringOptional

Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US. Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.speechify.ai/docs/language-support.

modelenumOptionalDefaults to simba-3.0

Model used for audio synthesis. Defaults to simba-3.0, which is streaming-native and multilingual: it officially supports English plus de-DE, es-ES, es-MX, fr-FR, it-IT and pt-BR, and routes each request to its English or its multilingual training based on language (falling back to the voice's locale when language is omitted). simba-3.2 is the streaming-native model with the lowest TTFB and richest expressivity, and the recommended Simba 3 model; it is English only, so a non-English voice returns 400.

The legacy Simba 1.6 models simba-english and simba-multilingual are retired from API version 2026-09-21: naming one returns 400 model_retired. Pinning your API version to a date before 2026-09-21 keeps them on their Simba 1.6 training until 2026-11-21; from then both ids are served by our current models on every API version that can still name them. Migrate to simba-3.2 (English) or simba-3.0 before then; call GET /v1/audio/models to see the set your workspace can select today.

Allowed values:
optionsobjectOptional
GetStreamOptionsRequest is the wrapper for request parameters to the client
output_formatenumOptional

The output audio format as a codec_sampleRate_bitrate string. Takes precedence over the Accept header when set, so you can request formats the Accept enum does not cover (e.g. pcm_16000, ulaw_8000). wav_* formats are not supported on streaming - use POST /v1/audio/speech for wav.

Response headers

Speechify-Request-IdstringOptional

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends a Speechify-Request-Id request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests

  • it is the stable handle that ties your observation to Speechify's server-side logs, and it matches the request_id field in the error envelope.

The legacy alias X-Request-ID carries the same value and is still accepted on requests, until 2027-07-24. Prefer the un-prefixed name (RFC 6648).

RateLimit-LimitintegerOptional

Request-rate budget: the maximum number of requests in the current window (the bucket capacity). The IETF-draft un-prefixed name; the legacy alias X-RateLimit-Limit carries the same value. Rides every response.

RateLimit-RemainingintegerOptional

Request-rate budget: requests left in the current window. Legacy alias: X-RateLimit-Remaining.

RateLimit-ResetintegerOptional

Request-rate budget: integer delta-seconds until the window fully refills (same unit as Retry-After). Legacy alias: X-RateLimit-Reset.

Server-TimingstringOptional

How much of the wait for this response was Speechify's, as W3C Server Timing metrics in milliseconds. ttfb runs from the request reaching the API to the first response byte, which on a streaming response is the first audio. model is the model's own time to first audio (the whole synthesis on a batch response) and is omitted when it was not measured. Whatever your client measures beyond ttfb is network distance and your own stack. Readable from browsers.

Response

Streamed audio. When output_format is set it selects the codec/sample rate; otherwise the Accept header does. The Content-Type reflects the selected format: it matches the Accept header, except raw PCM returns audio/L16 (with rate and channels parameters) and u-law returns audio/basic. A content policy refusal that lands after the audio has started aborts the transfer, so the client raises instead of completing the body; only a completed transfer was served in full.

Errors

400
Bad Request Error
401
Unauthorized Error
402
Payment Required Error
403
Forbidden Error
404
Not Found Error
409
Conflict Error
429
Too Many Requests Error
500
Internal Server Error
502
Bad Gateway Error
503
Service Unavailable Error