Skip to content

team-telnyx/ai / providers/claude/plugins/telnyx-tts/skills/telnyx-tts-python

telnyx-tts-python

Unverified

Generate speech from text using Telnyx and third-party TTS providers (AWS, Azure, ElevenLabs, MiniMax, Resemble, Rime, xAI). Returns base64-encoded audio or a binary stream. Also lists available voices per provider.

Telnyx Text-to-Speech - Python

Installation

pip install telnyx

Setup

import os
from telnyx import Telnyx

client = Telnyx(
    api_key=os.environ.get("TELNYX_API_KEY"),
)

All examples below assume client is already initialized as shown above.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

import telnyx

try:
    response = client.text_to_speech.generate(text="Hello world")
except telnyx.APIConnectionError:
    print("Network error — check connectivity and retry")
except telnyx.RateLimitError:
    import time
    time.sleep(1)
except telnyx.APIStatusError as e:
    print(f"API error {e.status_code}: {e.message}")

Common error codes: 401 invalid API key, 403 insufficient permissions, 404 resource not found, 422 validation error, 429 rate limited.

Core Tasks

Generate speech from text

Generate synthesized speech audio from text input. Returns audio as base64-encoded JSON (base64_output) or a binary audio stream (binary_output).

POST /text-to-speech/speech

ParameterTypeRequiredDescription
textstringYesThe text to synthesize.
providerenumNoTTS provider: telnyx, aws, azure, elevenlabs, minimax, resemble, rime. Default: telnyx.
voicestringNoVoice ID to use (e.g., en-US-Standard-A for AWS).
output_typeenumNobinary_output or base64_output. Default: binary_output.
text_typeenumNotext or ssml. Default: text.
languagestringNoLanguage code (e.g., en-US).
voice_settingsobjectNoAdvanced voice settings (speed, pitch, volume).
telnyxobjectNoTelnyx-specific provider options.
awsobjectNoAWS-specific provider options.
azureobjectNoAzure-specific provider options.
elevenlabsobjectNoElevenLabs-specific provider options.
minimaxobjectNoMiniMax-specific provider options.
resembleobjectNoResemble-specific provider options.
rimeobjectNoRime-specific provider options.
disable_cachebooleanNoDisable response caching.
# Default Telnyx provider
response = client.text_to_speech.generate(
    text="Hello from Telnyx!",
)
print(response.base64_audio)

# AWS provider with specific voice
response = client.text_to_speech.generate(
    text="Hello from Telnyx!",
    provider="aws",
    voice="en-US-Standard-A",
    output_type="base64_output",
)
print(response.base64_audio)

# SSML input
response = client.text_to_speech.generate(
    text="<speak>Hello <break time='1s'/> world</speak>",
    text_type="ssml",
)
print(response.base64_audio)

# ElevenLabs provider
response = client.text_to_speech.generate(
    text="Hello from Telnyx!",
    provider="elevenlabs",
    voice="21m00Tcm4TlvDq8ikWAM",
    output_type="base64_output",
)
print(response.base64_audio)

Primary response fields:

  • response.base64_audio — Base64-encoded audio data (when output_type is base64_output)
  • Binary stream (when output_type is binary_output)

List available voices

Retrieve a list of available voices from one or all TTS providers.

GET /text-to-speech/voices

ParameterTypeRequiredDescription
providerenumNoFilter by provider: telnyx, aws, azure, elevenlabs, minimax, resemble, rime.
# List all voices across all providers
response = client.text_to_speech.list_voices()
for voice in response.voices:
    print(f"{voice['name']} — {voice['provider']} ({voice['language']})")

# List only AWS voices
response = client.text_to_speech.list_voices(provider="aws")
for voice in response.voices:
    print(f"{voice['name']} — {voice['language']}")

Primary response fields:

  • response.voices — Array of voice objects with name, provider, language, voice_id

CLI Usage

The Telnyx Agent CLI provides composite commands for TTS:

# Generate speech
telnyx-agent tts --text "Hello world" --json

# Generate with specific provider and voice
telnyx-agent tts --text "Hello world" --provider aws --voice en-US-Standard-A --json

# List available voices
telnyx-agent tts-voices --json

# Filter voices by provider
telnyx-agent tts-voices --provider elevenlabs --json

Important Notes

  • Audio format: When output_type is base64_output, decode the base64 string to get the audio bytes. When binary_output, the response is a raw audio stream.
  • SSML: Use text_type: "ssml" to send SSML markup for fine-grained control over pronunciation, pauses, and emphasis.
  • Provider-specific options: Each provider (aws, azure, elevenlabs, etc.) has its own object for provider-specific configuration (e.g., AWS engine type, ElevenLabs stability).
  • Caching: Responses are cached by default. Use disable_cache: true to bypass.
  • xAI: The xAI provider is available via the CLI (--provider xai) and supports voice listing.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 318kUpdated Claude CodeCodexUnverifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 117kUpdated Claude CodeCodexUnverifiedInstall