text_to_speech
Convert text to audio speech using customizable voices and save the output as an audio file. Choose from multiple voice models, adjust speech parameters like speed and stability, and select output formats.
Instructions
Convert text to speech with a given voice and save the output audio file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop. Only one of voice_id or voice_name can be provided. If none are provided, the default voice will be used.
⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.
Args:
text (str): The text to convert to speech.
voice_name (str, optional): The name of the voice to use.
model_id (str, optional): The model ID to use for speech synthesis. Options include:
- eleven_multilingual_v2: High quality multilingual model (29 languages)
- eleven_flash_v2_5: Fastest model with ultra-low latency (32 languages)
- eleven_turbo_v2_5: Balanced quality and speed (32 languages)
- eleven_flash_v2: Fast English-only model
- eleven_turbo_v2: Balanced English-only model
- eleven_monolingual_v1: Legacy English model
Defaults to eleven_multilingual_v2 or environment variable ELEVENLABS_MODEL_ID.
stability (float, optional): Stability of the generated audio. Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. Range is 0 to 1.
similarity_boost (float, optional): Similarity boost of the generated audio. Determines how closely the AI should adhere to the original voice when attempting to replicate it. Range is 0 to 1.
style (float, optional): Style of the generated audio. Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. Range is 0 to 1.
use_speaker_boost (bool, optional): Use speaker boost of the generated audio. This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.
speed (float, optional): Speed of the generated audio. Controls the speed of the generated speech. Values range from 0.7 to 1.2, with 1.0 being the default speed. Lower values create slower, more deliberate speech while higher values produce faster-paced speech. Extreme values can impact the quality of the generated speech. Range is 0.7 to 1.2.
output_directory (str, optional): Directory where files should be saved.
Defaults to $HOME/Desktop if not provided.
language: ISO 639-1 language code for the voice.
output_format (str, optional): Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
Defaults to "mp3_44100_128". Must be one of:
mp3_22050_32
mp3_44100_32
mp3_44100_64
mp3_44100_96
mp3_44100_128
mp3_44100_192
pcm_8000
pcm_16000
pcm_22050
pcm_24000
pcm_44100
ulaw_8000
alaw_8000
opus_48000_32
opus_48000_64
opus_48000_96
opus_48000_128
opus_48000_192
Returns:
Text content with the path to the output file and name of the voice used.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | en | |
| model_id | No | ||
| output_directory | No | ||
| output_format | No | mp3_44100_128 | |
| similarity_boost | No | ||
| speed | No | ||
| stability | No | ||
| style | No | ||
| text | Yes | ||
| use_speaker_boost | No | ||
| voice_id | No | ||
| voice_name | No |
Implementation Reference
- elevenlabs_mcp/server.py:192-257 (handler)The core handler function for the 'text_to_speech' tool. Converts input text to speech using the ElevenLabs API, handles voice selection, generates audio with specified parameters, saves the output as an MP3 file, and returns the file path.
def text_to_speech( text: str, voice_name: str | None = None, output_directory: str | None = None, voice_id: str | None = None, stability: float = 0.5, similarity_boost: float = 0.75, style: float = 0, use_speaker_boost: bool = True, speed: float = 1.0, language: str = "en", output_format: str = "mp3_44100_128", model_id: str | None = None, ): if text == "": make_error("Text is required.") if voice_id is not None and voice_name is not None: make_error("voice_id and voice_name cannot both be provided.") voice = None if voice_id is not None: voice = client.voices.get(voice_id=voice_id) elif voice_name is not None: voices = client.voices.search(search=voice_name) if len(voices.voices) == 0: make_error("No voices found with that name.") voice = next((v for v in voices.voices if v.name == voice_name), None) if voice is None: make_error(f"Voice with name: {voice_name} does not exist.") voice_id = voice.voice_id if voice else DEFAULT_VOICE_ID output_path = make_output_path(output_directory, base_path) output_file_name = make_output_file("tts", text, output_path, "mp3") if model_id is None: model_id = ( "eleven_flash_v2_5" if language in ["hu", "no", "vi"] else "eleven_multilingual_v2" ) audio_data = client.text_to_speech.convert( text=text, voice_id=voice_id, model_id=model_id, output_format=output_format, voice_settings={ "stability": stability, "similarity_boost": similarity_boost, "style": style, "use_speaker_boost": use_speaker_boost, "speed": speed, }, ) audio_bytes = b"".join(audio_data) output_path.parent.mkdir(parents=True, exist_ok=True) with open(output_path / output_file_name, "wb") as f: f.write(audio_bytes) return TextContent( type="text", text=f"Success. File saved as: {output_path / output_file_name}. Voice used: {voice.name if voice else DEFAULT_VOICE_ID}", ) - elevenlabs_mcp/server.py:141-191 (registration)MCP tool registration decorator for 'text_to_speech', including comprehensive description that defines the input schema, parameters, and usage instructions.
@mcp.tool( description="""Convert text to speech with a given voice and save the output audio file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop. Only one of voice_id or voice_name can be provided. If none are provided, the default voice will be used. ⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user. Args: text (str): The text to convert to speech. voice_name (str, optional): The name of the voice to use. model_id (str, optional): The model ID to use for speech synthesis. Options include: - eleven_multilingual_v2: High quality multilingual model (29 languages) - eleven_flash_v2_5: Fastest model with ultra-low latency (32 languages) - eleven_turbo_v2_5: Balanced quality and speed (32 languages) - eleven_flash_v2: Fast English-only model - eleven_turbo_v2: Balanced English-only model - eleven_monolingual_v1: Legacy English model Defaults to eleven_multilingual_v2 or environment variable ELEVENLABS_MODEL_ID. stability (float, optional): Stability of the generated audio. Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. Range is 0 to 1. similarity_boost (float, optional): Similarity boost of the generated audio. Determines how closely the AI should adhere to the original voice when attempting to replicate it. Range is 0 to 1. style (float, optional): Style of the generated audio. Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. Range is 0 to 1. use_speaker_boost (bool, optional): Use speaker boost of the generated audio. This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency. speed (float, optional): Speed of the generated audio. Controls the speed of the generated speech. Values range from 0.7 to 1.2, with 1.0 being the default speed. Lower values create slower, more deliberate speech while higher values produce faster-paced speech. Extreme values can impact the quality of the generated speech. Range is 0.7 to 1.2. output_directory (str, optional): Directory where files should be saved. Defaults to $HOME/Desktop if not provided. language: ISO 639-1 language code for the voice. output_format (str, optional): Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. Defaults to "mp3_44100_128". Must be one of: mp3_22050_32 mp3_44100_32 mp3_44100_64 mp3_44100_96 mp3_44100_128 mp3_44100_192 pcm_8000 pcm_16000 pcm_22050 pcm_24000 pcm_44100 ulaw_8000 alaw_8000 opus_48000_32 opus_48000_64 opus_48000_96 opus_48000_128 opus_48000_192 Returns: Text content with the path to the output file and name of the voice used. """ )