Text To Speech

ElevenLabs Text-to-Speech

Generate natural speech from text - supports 90+ languages, multiple models for quality vs latency tradeoffs. Examples default to eleven_v4, the latest and highest-quality model.

Setup, before writing any code: if ELEVENLABS_API_KEY isn't set for this project, run npx -y @elevenlabs/cli@latest onboard init from the app's folder first and follow what it prints: it signs the user in and stores a key for the project, so nobody copies one by hand. Otherwise see the Installation Guide. For JavaScript, use @elevenlabs/* packages only.

Quick Start

Python

from elevenlabs import ElevenLabs

client = ElevenLabs()

audio = client.text_to_speech.convert(
    text="Hello, welcome to ElevenLabs!",
    voice_id="JBFqnCBsd6RMkjVDRZzb",  # George
    model_id="eleven_v4"
)

with open("output.mp3", "wb") as f:
    for chunk in audio:
        f.write(chunk)

JavaScript

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createWriteStream } from "fs";
import { Readable } from "stream";

const client = new ElevenLabsClient();
const audio = await client.textToSpeech.convert("JBFqnCBsd6RMkjVDRZzb", {
  text: "Hello, welcome to ElevenLabs!",
  modelId: "eleven_v4",
});
// convert() returns a web ReadableStream — bridge it to a Node stream to write to disk
Readable.fromWeb(audio).pipe(createWriteStream("output.mp3"));

CLI

Use say to play text immediately with the default voice and eleven_v3 model:

elevenlabs say "Hello!"

Pipe text into say when another command produces the input:

echo "The build finished successfully." | elevenlabs say

Use the API command when you need to set request parameters directly:

elevenlabs text-to-speech convert --voice-id JBFqnCBsd6RMkjVDRZzb \
  --text "Hello!" --model-id eleven_v4 --output output.mp3

The CLI reads ELEVENLABS_API_KEY from the environment automatically.

Models

Model ID	Languages	Latency	Best For
eleven_v4	90+	Standard	Default. Highest quality, emotional range, audio tags, voice cloning accuracy
eleven_v4_turbo	90+	~100ms	Real-time v4 quality for agents and interactive apps (via Text to Dialogue WebSocket)
eleven_flash_v2_5	32	~75ms	Lowest latency, lowest cost, stream-input WebSocket
eleven_flash_v2	English	~75ms	English-only, lowest latency
eleven_multilingual_v2	29	Standard	Previous generation; most stable on very long-form generations
eleven_v3	70+	Standard	Previous generation expressive model

eleven_turbo_v2_5 and eleven_turbo_v2 are superseded by the Flash models (same output, lower latency) — use eleven_flash_v2_5 / eleven_flash_v2 instead.

Eleven v4 notes: supports only stability and similarity_boost voice settings (no style or speed), does not support SSML, and is not available on the stream-input TTS WebSocket. Direct delivery with audio tags such as [whispers], [laughs], [sarcastic].

Voice IDs

Use pre-made voices or create custom voices in the dashboard.

Popular voices:

• JBFqnCBsd6RMkjVDRZzb - George (male, narrative)
• EXAVITQu4vr4xnSDxMaL - Sarah (female, soft)
• onwK4e9ZLuTAKqWW03F9 - Daniel (male, authoritative)
• XB0fDUnXU5powFXDhCwa - Charlotte (female, conversational)

voices = client.voices.get_all()
for voice in voices.voices:
    print(f"{voice.voice_id}: {voice.name}")

Voice Settings

Fine-tune how the voice sounds:

• Stability: How consistent the voice stays. Lower values = more emotional range and variation, but can sound unstable. Higher = steady, predictable delivery.
• Similarity boost: How closely to match the original voice sample. Higher values sound more like the original but may amplify audio artifacts.
• Style: Exaggerates the voice's unique style characteristics (v2/v3 models; not supported on Eleven v4).
• Speed: Speech speed multiplier (v2/v3 models; not supported on Eleven v4).
• Speaker boost: Post-processing that enhances clarity and voice similarity.

from elevenlabs import VoiceSettings

audio = client.text_to_speech.convert(
    text="Customize my voice settings.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    voice_settings=VoiceSettings(
        stability=0.5,          # Lower = more expressive, higher = more consistent
        similarity_boost=0.75,  # Higher = closer to the reference voice
    )
)

Language Selection

Use language_code with models that support language enforcement to guide pronunciation and text normalization. Unsupported language codes are ignored, and language_code is not supported on eleven_multilingual_v2.

audio = client.text_to_speech.convert(
    text="Bonjour, comment allez-vous?",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    language_code="fr"  # ISO 639-1 code
)

Text Normalization

Controls how numbers, dates, and abbreviations are converted to spoken words. For example, "01/15/2026" becomes "January fifteenth, twenty twenty-six":

• "auto" (default): Model decides based on context
• "on": Always normalize (use when you want natural speech)
• "off": Speak literally (use when you want "zero one slash one five...")

audio = client.text_to_speech.convert(
    text="Call 1-800-555-0123 on 01/15/2026",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    apply_text_normalization="on"
)

Audio Effects

Use audio_effects to process the generated audio with a filter preset, perceived distance, a reverb environment, a looped background noise bed, and stereo panning. Effects do not change the cost of a request.

Field	Range	Description
filter_preset_id	Catalog ID	Filter that colors the voice, such as phone or old_radio
distance	0-1 (default 0)	How far the speaker sounds from the microphone
environment_id	Catalog ID	Reverb environment, such as small_room or hall
send_level	0-1 (default 1)	How much of the voice feeds the reverb; 0 turns reverb off
background_noise_id	Catalog ID	Background noise looped under the voice, such as cafe or keyboard
pan	-1 to 1 (default 0)	Stereo position of the voice, from hard left to hard right

List valid filter preset, environment, and background noise IDs with the catalog endpoint (GET /v1/audio-effects/catalog):

from elevenlabs import EffectsSpecInput

catalog = client.audio_effects.get_catalog()
for environment in catalog.environments:
    print(f"{environment.environment_id}: {environment.name}")

audio = client.text_to_speech.convert(
    text="Welcome to the concert hall.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    audio_effects=EffectsSpecInput(
        environment_id="hall",
        distance=0.3,
        pan=-0.5,
    )
)

Reverb and non-zero pan produce stereo audio and are rejected for ulaw_*, alaw_*, and pcm_* output formats. Unknown effect IDs return a 404 error.

Request Stitching

When generating long audio in multiple requests, the audio can have pops, unnatural pauses, or tone shifts at the boundaries. Request stitching solves this by letting each request know what comes before/after it:

# First request
audio1 = client.text_to_speech.convert(
    text="This is the first part.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    next_text="And this continues the story."
)

# Second request using previous context
audio2 = client.text_to_speech.convert(
    text="And this continues the story.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4",
    previous_text="This is the first part."
)

Output Formats

Format	Description
mp3_44100_128	MP3 44.1kHz 128kbps (default) - compressed, good for web/apps
mp3_44100_192	MP3 44.1kHz 192kbps (Creator+) - higher quality compressed
mp3_44100_64	MP3 44.1kHz 64kbps - lower quality, smaller files
mp3_22050_32	MP3 22.05kHz 32kbps - smallest MP3 files
pcm_16000	Raw PCM 16kHz - use for real-time processing
pcm_22050	Raw PCM 22.05kHz
pcm_24000	Raw PCM 24kHz - good balance for streaming
pcm_44100	Raw PCM 44.1kHz (Pro+) - CD quality
pcm_48000	Raw PCM 48kHz (Pro+) - highest quality
ulaw_8000	μ-law 8kHz - standard for phone systems (Twilio, telephony)
alaw_8000	A-law 8kHz - telephony (alternative to μ-law)
opus_48000_64	Opus 48kHz 64kbps - efficient streaming codec
wav_44100	WAV 44.1kHz - uncompressed with headers

Streaming

Use the stream method to receive audio chunks as they're generated:

audio_stream = client.text_to_speech.stream(
    text="This text will be streamed as audio.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_v4"
)

for chunk in audio_stream:
    play_audio(chunk)

For real-time apps where latency matters most, use eleven_v4_turbo (~100ms) over the Text to Dialogue WebSocket, or eleven_flash_v2_5 (~75ms) over HTTP streaming or the stream-input WebSocket. See references/streaming.md.

Error Handling

try:
    audio = client.text_to_speech.convert(
        text="Generate speech",
        voice_id="invalid-voice-id",
        model_id="eleven_v4"
    )
except Exception as e:
    print(f"API error: {e}")

Common errors:

• 401: Invalid API key
• 422: Invalid parameters (check voice_id, model_id)
• 429: Rate limit exceeded

Tracking Costs

Monitor character usage via response headers (x-character-count, request-id):

response = client.text_to_speech.convert.with_raw_response(
    text="Hello!", voice_id="JBFqnCBsd6RMkjVDRZzb", model_id="eleven_v4"
)
audio = response.parse()
print(f"Characters used: {response.headers.get('x-character-count')}")

References

• Installation Guide
• Streaming Audio
• Voice Settings