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
Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.
Headers
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.
Request
Plain text or SSML to be synthesized to speech.
Up to 20,000 characters of spoken text, the characters the request is billed for: SSML tags do not count. The input as sent, markup included, may be up to 32,000 characters.
Refer to https://docs.speechify.ai/docs/api-limits for the input size limits.
SSML sets pauses (<break>), speaking rate, pitch and volume (<prosody>) and pronunciation (<sub alias>): see https://docs.speechify.ai/build/guides/text-to-speech/ssml for each tag. Emotion styles and emphasis are applied only by the Simba 1.6 models, until 2026-11-21; simba-3.0, simba-3.2 and simba-3.5 accept those tags without applying them.
Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
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.
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 English model; a non-English voice returns 400. simba-3.5 is the recommended model: streaming-native, covering 48 languages under one id, English included, routed by language like simba-3.0; every voice works on it, cloned voices included.
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), simba-3.0 or simba-3.5 before then; call GET /v1/audio/models to see the set your workspace can select today.
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.
Optional. How to pronounce words and phrases in input: each entry gives a text and either the phones to say it with (ipa) or plain text to say in its place (alias). Every entry applies to the whole request.
Supported only in the languages a model’s entry in GET /v1/audio/models lists in pronunciation_languages, which does not include English yet: any other model or language returns 400 pronunciations_unsupported. An empty array is accepted by every model in every language. At most 200 entries. A malformed entry, a phone outside the model’s phone set, an ipa entry whose text is more than one word, or two entries for the same text returns 400 validation_failed, with fields naming each entry (for example pronunciations[3].ipa), before anything is synthesized or billed. So does an input longer than 20,000 characters once every alias stands in for its text.
Entries match case-insensitively unless case_sensitive is true, as whole words, except in Chinese, Japanese, Korean, Thai, Lao, Khmer and Burmese, where they match anywhere in the text; the longest matching entry wins, and an entry takes precedence over the model’s own pronunciation. Pronunciations are not billed, and speech marks still index input exactly as sent. See https://docs.speechify.ai/build/guides/text-to-speech/pronunciation.
Optional. A stable, opaque identifier for the end user this request is made for: a hash of your own user id or an opaque id, never an email address or other personal data. It is recorded with the request even under zero data retention, and your workspace can be given per-end-user limits and a block list keyed on it. See https://docs.speechify.ai/build/guides/concepts/safety-identifiers.
Response headers
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_idfield 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).
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.
Request-rate budget: requests left in the current window. Legacy
alias: X-RateLimit-Remaining.
Request-rate budget: integer delta-seconds until the window fully
refills (same unit as Retry-After). Legacy alias:
X-RateLimit-Reset.
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.