elevenlabs/tts

ElevenLabs text to speech. Reads text aloud in one of 21 built-in voices, across 29 languages on the default model and up to 74 on Eleven v3.

$0.05 / request
GPU: A100

Model Inputs

string

The text to speak. Billed per character; the pool's free accounts hold 10,000 characters each

string

One of the 21 built-in ElevenLabs voices. All are English speakers, but they read other languages accurately with a multilingual model, in an English accent

string

Synthesis model. multilingual_v2 is the most stable for long text (29 languages), v3 is the most expressive and understands [audio tags] (74 languages, 5,000 characters), flash/turbo are the fastest

string

Audio container, as codec_samplerate_bitrate. Higher-fidelity formats (mp3_44100_192, pcm_44100, wav_44100) need a paid ElevenLabs tier and are not available here

number

How steady the delivery is. Lower is more emotional and more variable between generations, higher is more monotone

number

How closely the output sticks to the original voice

number

Style exaggeration. Anything above 0 costs extra latency

boolean

Boost similarity to the original speaker, at a small latency cost

number

Speaking rate. 1.0 is normal; the API accepts 0.7 to 1.2 and refuses anything outside it

string

ISO 639-1 code forcing a language for synthesis and text normalization, e.g. 'ja'. Ignored by eleven_multilingual_v2, which detects the language itself

string

Whether numbers, dates and abbreviations are spelled out before being spoken. 'auto' lets the model decide

integer

Best-effort deterministic sampling: the same seed, text and settings return the same audio. Determinism is not guaranteed

Result

Idle
Waiting for your input...

Pricing

elevenlabs/

tts

Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.

Output
$0.05 / request
or
20 requests / $1

For example, generating 100 requests costs about $5.00.

Check out our docs for more information about how per-request pricing works on Synexa.

ProviderPrice ($)Saving (%)
Synexa$0.05-
fal$0.05same price

Readme

ElevenLabs text to speech, running on our own pool of ElevenLabs accounts. Give it text and one of 21 built-in voices and it reads the text aloud, with per-character timings recovered from the upstream with-timestamps endpoint.

Capabilities:

  • 29 languages on the default eleven_multilingual_v2, up to 74 on the eleven_v3 models
  • Seven synthesis models spanning the tradeoff: eleven_multilingual_v2 for stable long-form, eleven_v3 for the most expressive read (it understands inline [audio tags]), eleven_flash_v2_5 for the lowest latency
  • Delivery control through stability, similarity_boost, style, use_speaker_boost and speed
  • Thirteen output containers, from mp3_22050_32 up to mp3_44100_128, plus PCM, WAV, Opus and telephony u-law/a-law
  • seed asks for best-effort determinism, so the same text and settings return the same audio

Usage notes:

  • All 21 voices are English speakers. They read other languages accurately with a multilingual model, in an English accent — there is no native-accent voice here
  • text is capped at 5,000 characters for the two eleven_v3 models and 10,000 for the rest; longer text is rejected before the request is made
  • speed is accepted between 0.7 and 1.2 only
  • language_code forces a language on the flash and turbo models; eleven_multilingual_v2 detects the language itself and ignores it
  • High-fidelity formats (mp3_44100_192, pcm_44100, wav_44100) are not offered — they require a paid ElevenLabs tier